Skip to content

GitLab

Unverified Commit be4afa0b authored by Mark Van Aken's avatar Mark Van Aken Committed by GitHub
Browse files

#7535 Update FloatTensor type hints to Tensor (#7883) 

* find & replace all FloatTensors to Tensor

* apply formatting

* Update torch.FloatTensor to torch.Tensor in the remaining files

* formatting

* Fix the rest of the places where FloatTensor is used as well as in documentation

* formatting

* Update new file from FloatTensor to Tensor
parent 04f4bd54
Hide whitespace changes
Inline Side-by-side
Showing with 305 additions and 305 deletions
src/diffusers/pipelines/blip_diffusion/pipeline_blip_diffusion.py
View file @ be4afa0b
......@@ -191,7 +191,7 @@ class BlipDiffusionPipeline(DiffusionPipeline):
reference_image: PIL.Image.Image,
source_subject_category: List[str],
target_subject_category: List[str],
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
guidance_scale: float = 7.5,
height: int = 512,
width: int = 512,
......@@ -215,7 +215,7 @@ class BlipDiffusionPipeline(DiffusionPipeline):
The source subject category.
target_subject_category (`List[str]`):
The target subject category.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor will ge generated by random sampling.
......
src/diffusers/pipelines/consistency_models/pipeline_consistency_models.py
View file @ be4afa0b
......@@ -105,7 +105,7 @@ class ConsistencyModelPipeline(DiffusionPipeline):
return latents
# Follows diffusers.VaeImageProcessor.postprocess
def postprocess_image(self, sample: torch.FloatTensor, output_type: str = "pil"):
def postprocess_image(self, sample: torch.Tensor, output_type: str = "pil"):
if output_type not in ["pt", "np", "pil"]:
raise ValueError(
f"output_type={output_type} is not supported. Make sure to choose one of ['pt', 'np', or 'pil']"
......@@ -173,10 +173,10 @@ class ConsistencyModelPipeline(DiffusionPipeline):
num_inference_steps: int = 1,
timesteps: List[int] = None,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
):
r"""
......@@ -195,7 +195,7 @@ class ConsistencyModelPipeline(DiffusionPipeline):
generator (`torch.Generator`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
......@@ -205,7 +205,7 @@ class ConsistencyModelPipeline(DiffusionPipeline):
Whether or not to return a [`~pipelines.ImagePipelineOutput`] instead of a plain tuple.
callback (`Callable`, *optional*):
A function that calls every `callback_steps` steps during inference. The function is called with the
following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function is called. If not specified, the callback is called at
every step.
......
src/diffusers/pipelines/controlnet/multicontrolnet.py
View file @ be4afa0b
......@@ -31,7 +31,7 @@ class MultiControlNetModel(ModelMixin):
def forward(
self,
sample: torch.FloatTensor,
sample: torch.Tensor,
timestep: Union[torch.Tensor, float, int],
encoder_hidden_states: torch.Tensor,
controlnet_cond: List[torch.tensor],
......
src/diffusers/pipelines/controlnet/pipeline_controlnet.py
View file @ be4afa0b
......@@ -261,8 +261,8 @@ class StableDiffusionControlNetPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
**kwargs,
):
......@@ -294,8 +294,8 @@ class StableDiffusionControlNetPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -315,10 +315,10 @@ class StableDiffusionControlNetPipeline(
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -846,7 +846,7 @@ class StableDiffusionControlNetPipeline(
# Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
def get_guidance_scale_embedding(
self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
) -> torch.FloatTensor:
) -> torch.Tensor:
"""
See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
......@@ -859,7 +859,7 @@ class StableDiffusionControlNetPipeline(
Data type of the generated embeddings.
Returns:
`torch.FloatTensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
`torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
"""
assert len(w.shape) == 1
w = w * 1000.0
......@@ -913,11 +913,11 @@ class StableDiffusionControlNetPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
ip_adapter_image: Optional[PipelineImageInput] = None,
ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -936,14 +936,14 @@ class StableDiffusionControlNetPipeline(
Args:
prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
`init`, images must be passed as a list such that each element of the list can be correctly batched for
input to a single ControlNet. When `prompt` is a list, and if a list of images is passed for a single
specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
images must be passed as a list such that each element of the list can be correctly batched for input
to a single ControlNet. When `prompt` is a list, and if a list of images is passed for a single
ControlNet, each will be paired with each prompt in the `prompt` list. This also applies to multiple
ControlNets, where a list of image lists can be passed to batch for each prompt and each ControlNet.
height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
......@@ -975,18 +975,18 @@ class StableDiffusionControlNetPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
......@@ -998,7 +998,7 @@ class StableDiffusionControlNetPipeline(
plain tuple.
callback (`Callable`, *optional*):
A function that calls every `callback_steps` steps during inference. The function is called with the
following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function is called. If not specified, the callback is called at
every step.
......
src/diffusers/pipelines/controlnet/pipeline_controlnet_blip_diffusion.py
View file @ be4afa0b
......@@ -240,7 +240,7 @@ class BlipDiffusionControlNetPipeline(DiffusionPipeline):
condtioning_image: PIL.Image.Image,
source_subject_category: List[str],
target_subject_category: List[str],
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
guidance_scale: float = 7.5,
height: int = 512,
width: int = 512,
......@@ -266,7 +266,7 @@ class BlipDiffusionControlNetPipeline(DiffusionPipeline):
The source subject category.
target_subject_category (`List[str]`):
The target subject category.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor will ge generated by random sampling.
......
src/diffusers/pipelines/controlnet/pipeline_controlnet_img2img.py
View file @ be4afa0b
......@@ -239,8 +239,8 @@ class StableDiffusionControlNetImg2ImgPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
**kwargs,
):
......@@ -272,8 +272,8 @@ class StableDiffusionControlNetImg2ImgPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -293,10 +293,10 @@ class StableDiffusionControlNetImg2ImgPipeline(
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -904,11 +904,11 @@ class StableDiffusionControlNetImg2ImgPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
ip_adapter_image: Optional[PipelineImageInput] = None,
ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -927,18 +927,18 @@ class StableDiffusionControlNetImg2ImgPipeline(
Args:
prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The initial image to be used as the starting point for the image generation process. Can also accept
image latents as `image`, and if passing latents directly they are not encoded again.
control_image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
control_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
`init`, images must be passed as a list such that each element of the list can be correctly batched for
input to a single ControlNet.
specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
images must be passed as a list such that each element of the list can be correctly batched for input
to a single ControlNet.
height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
......@@ -966,18 +966,18 @@ class StableDiffusionControlNetImg2ImgPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
......
src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint.py
View file @ be4afa0b
......@@ -364,8 +364,8 @@ class StableDiffusionControlNetInpaintPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
**kwargs,
):
......@@ -397,8 +397,8 @@ class StableDiffusionControlNetInpaintPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -418,10 +418,10 @@ class StableDiffusionControlNetInpaintPipeline(
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -1121,11 +1121,11 @@ class StableDiffusionControlNetInpaintPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
ip_adapter_image: Optional[PipelineImageInput] = None,
ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -1144,14 +1144,14 @@ class StableDiffusionControlNetInpaintPipeline(
Args:
prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`,
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`,
`List[PIL.Image.Image]`, or `List[np.ndarray]`):
`Image`, NumPy array or tensor representing an image batch to be used as the starting point. For both
NumPy array and PyTorch tensor, the expected value range is between `[0, 1]`. If it's a tensor or a
list or tensors, the expected shape should be `(B, C, H, W)` or `(C, H, W)`. If it is a NumPy array or
a list of arrays, the expected shape should be `(B, H, W, C)` or `(H, W, C)`. It can also accept image
latents as `image`, but if passing latents directly it is not encoded again.
mask_image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`,
mask_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`,
`List[PIL.Image.Image]`, or `List[np.ndarray]`):
`Image`, NumPy array or tensor representing an image batch to mask `image`. White pixels in the mask
are repainted while black pixels are preserved. If `mask_image` is a PIL image, it is converted to a
......@@ -1159,14 +1159,14 @@ class StableDiffusionControlNetInpaintPipeline(
color channel (L) instead of 3, so the expected shape for PyTorch tensor would be `(B, 1, H, W)`, `(B,
H, W)`, `(1, H, W)`, `(H, W)`. And for NumPy array, it would be for `(B, H, W, 1)`, `(B, H, W)`, `(H,
W, 1)`, or `(H, W)`.
control_image (`torch.FloatTensor`, `PIL.Image.Image`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`,
`List[List[torch.FloatTensor]]`, or `List[List[PIL.Image.Image]]`):
control_image (`torch.Tensor`, `PIL.Image.Image`, `List[torch.Tensor]`, `List[PIL.Image.Image]`,
`List[List[torch.Tensor]]`, or `List[List[PIL.Image.Image]]`):
The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
`init`, images must be passed as a list such that each element of the list can be correctly batched for
input to a single ControlNet.
specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
images must be passed as a list such that each element of the list can be correctly batched for input
to a single ControlNet.
height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
......@@ -1201,18 +1201,18 @@ class StableDiffusionControlNetInpaintPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
......
src/diffusers/pipelines/controlnet/pipeline_controlnet_inpaint_sd_xl.py
View file @ be4afa0b
......@@ -261,10 +261,10 @@ class StableDiffusionXLControlNetInpaintPipeline(
do_classifier_free_guidance: bool = True,
negative_prompt: Optional[str] = None,
negative_prompt_2: Optional[str] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -290,17 +290,17 @@ class StableDiffusionXLControlNetInpaintPipeline(
negative_prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
`text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
If not provided, pooled text embeddings will be generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
input argument.
......@@ -1157,13 +1157,13 @@ class StableDiffusionXLControlNetInpaintPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
ip_adapter_image: Optional[PipelineImageInput] = None,
ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -1250,23 +1250,23 @@ class StableDiffusionXLControlNetInpaintPipeline(
negative_prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
`text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
provided, embeddings are computed from the `ip_adapter_image` input argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
If not provided, pooled text embeddings will be generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
input argument.
......@@ -1278,7 +1278,7 @@ class StableDiffusionXLControlNetInpaintPipeline(
generator (`torch.Generator`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor will ge generated by sampling using the supplied random `generator`.
......
src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl.py
View file @ be4afa0b
......@@ -233,10 +233,10 @@ class StableDiffusionXLControlNetPipeline(
do_classifier_free_guidance: bool = True,
negative_prompt: Optional[str] = None,
negative_prompt_2: Optional[str] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -262,17 +262,17 @@ class StableDiffusionXLControlNetPipeline(
negative_prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
`text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
If not provided, pooled text embeddings will be generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
input argument.
......@@ -876,7 +876,7 @@ class StableDiffusionXLControlNetPipeline(
# Copied from diffusers.pipelines.latent_consistency_models.pipeline_latent_consistency_text2img.LatentConsistencyModelPipeline.get_guidance_scale_embedding
def get_guidance_scale_embedding(
self, w: torch.Tensor, embedding_dim: int = 512, dtype: torch.dtype = torch.float32
) -> torch.FloatTensor:
) -> torch.Tensor:
"""
See https://github.com/google-research/vdm/blob/dc27b98a554f65cdc654b800da5aa1846545d41b/model_vdm.py#L298
......@@ -889,7 +889,7 @@ class StableDiffusionXLControlNetPipeline(
Data type of the generated embeddings.
Returns:
`torch.FloatTensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
`torch.Tensor`: Embedding vectors with shape `(len(w), embedding_dim)`.
"""
assert len(w.shape) == 1
w = w * 1000.0
......@@ -948,13 +948,13 @@ class StableDiffusionXLControlNetPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
ip_adapter_image: Optional[PipelineImageInput] = None,
ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -982,14 +982,14 @@ class StableDiffusionXLControlNetPipeline(
prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts to be sent to `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
used in both text-encoders.
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
`init`, images must be passed as a list such that each element of the list can be correctly batched for
input to a single ControlNet.
specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
images must be passed as a list such that each element of the list can be correctly batched for input
to a single ControlNet.
height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image. Anything below 512 pixels won't work well for
[stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
......@@ -1025,25 +1025,25 @@ class StableDiffusionXLControlNetPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, pooled text embeddings are generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs (prompt
weighting). If not provided, pooled `negative_prompt_embeds` are generated from `negative_prompt` input
argument.
ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
......
src/diffusers/pipelines/controlnet/pipeline_controlnet_sd_xl_img2img.py
View file @ be4afa0b
......@@ -287,10 +287,10 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
do_classifier_free_guidance: bool = True,
negative_prompt: Optional[str] = None,
negative_prompt_2: Optional[str] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -316,17 +316,17 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
negative_prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
`text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
If not provided, pooled text embeddings will be generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
input argument.
......@@ -1082,13 +1082,13 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
ip_adapter_image: Optional[PipelineImageInput] = None,
ip_adapter_image_embeds: Optional[List[torch.FloatTensor]] = None,
ip_adapter_image_embeds: Optional[List[torch.Tensor]] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -1119,18 +1119,18 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts to be sent to the `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
used in both text-encoders
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The initial image will be used as the starting point for the image generation process. Can also accept
image latents as `image`, if passing latents directly, it will not be encoded again.
control_image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
control_image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The ControlNet input condition. ControlNet uses this input condition to generate guidance to Unet. If
the type is specified as `Torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can
also be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If
height and/or width are passed, `image` is resized according to them. If multiple ControlNets are
specified in init, images must be passed as a list such that each element of the list can be correctly
batched for input to a single controlnet.
the type is specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also
be accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
and/or width are passed, `image` is resized according to them. If multiple ControlNets are specified in
init, images must be passed as a list such that each element of the list can be correctly batched for
input to a single controlnet.
height (`int`, *optional*, defaults to the size of control_image):
The height in pixels of the generated image. Anything below 512 pixels won't work well for
[stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
......@@ -1169,26 +1169,26 @@ class StableDiffusionXLControlNetImg2ImgPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor will ge generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
If not provided, pooled text embeddings will be generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
input argument.
ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
ip_adapter_image_embeds (`List[torch.FloatTensor]`, *optional*):
ip_adapter_image_embeds (`List[torch.Tensor]`, *optional*):
Pre-generated image embeddings for IP-Adapter. It should be a list of length same as number of
IP-adapters. Each element should be a tensor of shape `(batch_size, num_images, emb_dim)`. It should
contain the negative image embedding if `do_classifier_free_guidance` is set to `True`. If not
......
src/diffusers/pipelines/controlnet_xs/pipeline_controlnet_xs.py
View file @ be4afa0b
......@@ -188,8 +188,8 @@ class StableDiffusionControlNetXSPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
**kwargs,
):
......@@ -221,8 +221,8 @@ class StableDiffusionControlNetXSPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -242,10 +242,10 @@ class StableDiffusionControlNetXSPipeline(
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -638,9 +638,9 @@ class StableDiffusionControlNetXSPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -657,14 +657,14 @@ class StableDiffusionControlNetXSPipeline(
Args:
prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide image generation. If not defined, you need to pass `prompt_embeds`.
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
`init`, images must be passed as a list such that each element of the list can be correctly batched for
input to a single ControlNet.
specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
images must be passed as a list such that each element of the list can be correctly batched for input
to a single ControlNet.
height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
......@@ -686,14 +686,14 @@ class StableDiffusionControlNetXSPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
output_type (`str`, *optional*, defaults to `"pil"`):
......
src/diffusers/pipelines/controlnet_xs/pipeline_controlnet_xs_sd_xl.py
View file @ be4afa0b
......@@ -213,10 +213,10 @@ class StableDiffusionXLControlNetXSPipeline(
do_classifier_free_guidance: bool = True,
negative_prompt: Optional[str] = None,
negative_prompt_2: Optional[str] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -242,17 +242,17 @@ class StableDiffusionXLControlNetXSPipeline(
negative_prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation to be sent to `tokenizer_2` and
`text_encoder_2`. If not defined, `negative_prompt` is used in both text-encoders
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting.
If not provided, pooled text embeddings will be generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, pooled negative_prompt_embeds will be generated from `negative_prompt`
input argument.
......@@ -721,11 +721,11 @@ class StableDiffusionXLControlNetXSPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_pooled_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
pooled_prompt_embeds: Optional[torch.Tensor] = None,
negative_pooled_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -751,14 +751,14 @@ class StableDiffusionXLControlNetXSPipeline(
prompt_2 (`str` or `List[str]`, *optional*):
The prompt or prompts to be sent to `tokenizer_2` and `text_encoder_2`. If not defined, `prompt` is
used in both text-encoders.
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.FloatTensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, `List[np.ndarray]`,:
`List[List[torch.Tensor]]`, `List[List[np.ndarray]]` or `List[List[PIL.Image.Image]]`):
The ControlNet input condition to provide guidance to the `unet` for generation. If the type is
specified as `torch.FloatTensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be
accepted as an image. The dimensions of the output image defaults to `image`'s dimensions. If height
and/or width are passed, `image` is resized accordingly. If multiple ControlNets are specified in
`init`, images must be passed as a list such that each element of the list can be correctly batched for
input to a single ControlNet.
specified as `torch.Tensor`, it is passed to ControlNet as is. `PIL.Image.Image` can also be accepted
as an image. The dimensions of the output image defaults to `image`'s dimensions. If height and/or
width are passed, `image` is resized accordingly. If multiple ControlNets are specified in `init`,
images must be passed as a list such that each element of the list can be correctly batched for input
to a single ControlNet.
height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
The height in pixels of the generated image. Anything below 512 pixels won't work well for
[stabilityai/stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)
......@@ -787,20 +787,20 @@ class StableDiffusionXLControlNetXSPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, pooled text embeddings are generated from `prompt` input argument.
negative_pooled_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_pooled_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs (prompt
weighting). If not provided, pooled `negative_prompt_embeds` are generated from `negative_prompt` input
argument.
......
src/diffusers/pipelines/deepfloyd_if/pipeline_if.py
View file @ be4afa0b
......@@ -164,8 +164,8 @@ class IFPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: int = 1,
device: Optional[torch.device] = None,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
clean_caption: bool = False,
):
r"""
......@@ -184,10 +184,10 @@ class IFPipeline(DiffusionPipeline, LoraLoaderMixin):
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -549,11 +549,11 @@ class IFPipeline(DiffusionPipeline, LoraLoaderMixin):
width: Optional[int] = None,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
clean_caption: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -593,10 +593,10 @@ class IFPipeline(DiffusionPipeline, LoraLoaderMixin):
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -607,7 +607,7 @@ class IFPipeline(DiffusionPipeline, LoraLoaderMixin):
Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
callback (`Callable`, *optional*):
A function that will be called every `callback_steps` steps during inference. The function will be
called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function will be called. If not specified, the callback will be
called at every step.
......
src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img.py
View file @ be4afa0b
......@@ -188,8 +188,8 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: int = 1,
device: Optional[torch.device] = None,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
clean_caption: bool = False,
):
r"""
......@@ -208,10 +208,10 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -421,7 +421,7 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -665,11 +665,11 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
clean_caption: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -681,7 +681,7 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
instead.
image (`torch.FloatTensor` or `PIL.Image.Image`):
image (`torch.Tensor` or `PIL.Image.Image`):
`Image`, or tensor representing an image batch, that will be used as the starting point for the
process.
strength (`float`, *optional*, defaults to 0.7):
......@@ -714,10 +714,10 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -728,7 +728,7 @@ class IFImg2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
callback (`Callable`, *optional*):
A function that will be called every `callback_steps` steps during inference. The function will be
called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function will be called. If not specified, the callback will be
called at every step.
......
src/diffusers/pipelines/deepfloyd_if/pipeline_if_img2img_superresolution.py
View file @ be4afa0b
......@@ -340,8 +340,8 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: int = 1,
device: Optional[torch.device] = None,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
clean_caption: bool = False,
):
r"""
......@@ -360,10 +360,10 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -576,7 +576,7 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -607,7 +607,7 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`original_image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`original_image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -735,7 +735,7 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
image: Union[PIL.Image.Image, np.ndarray, torch.FloatTensor],
image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],
original_image: Union[
PIL.Image.Image, torch.Tensor, np.ndarray, List[PIL.Image.Image], List[torch.Tensor], List[np.ndarray]
] = None,
......@@ -748,11 +748,11 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
noise_level: int = 250,
......@@ -762,10 +762,10 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
Function invoked when calling the pipeline for generation.
Args:
image (`torch.FloatTensor` or `PIL.Image.Image`):
image (`torch.Tensor` or `PIL.Image.Image`):
`Image`, or tensor representing an image batch, that will be used as the starting point for the
process.
original_image (`torch.FloatTensor` or `PIL.Image.Image`):
original_image (`torch.Tensor` or `PIL.Image.Image`):
The original image that `image` was varied from.
strength (`float`, *optional*, defaults to 0.8):
Conceptually, indicates how much to transform the reference `image`. Must be between 0 and 1. `image`
......@@ -800,10 +800,10 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -814,7 +814,7 @@ class IFImg2ImgSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
callback (`Callable`, *optional*):
A function that will be called every `callback_steps` steps during inference. The function will be
called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function will be called. If not specified, the callback will be
called at every step.
......
src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting.py
View file @ be4afa0b
......@@ -192,8 +192,8 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: int = 1,
device: Optional[torch.device] = None,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
clean_caption: bool = False,
):
r"""
......@@ -212,10 +212,10 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -428,7 +428,7 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -459,7 +459,7 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`mask_image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`mask_image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -760,11 +760,11 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
clean_caption: bool = True,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -776,7 +776,7 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
instead.
image (`torch.FloatTensor` or `PIL.Image.Image`):
image (`torch.Tensor` or `PIL.Image.Image`):
`Image`, or tensor representing an image batch, that will be used as the starting point for the
process.
mask_image (`PIL.Image.Image`):
......@@ -814,10 +814,10 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -828,7 +828,7 @@ class IFInpaintingPipeline(DiffusionPipeline, LoraLoaderMixin):
Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
callback (`Callable`, *optional*):
A function that will be called every `callback_steps` steps during inference. The function will be
called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function will be called. If not specified, the callback will be
called at every step.
......
src/diffusers/pipelines/deepfloyd_if/pipeline_if_inpainting_superresolution.py
View file @ be4afa0b
......@@ -342,8 +342,8 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: int = 1,
device: Optional[torch.device] = None,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
clean_caption: bool = False,
):
r"""
......@@ -362,10 +362,10 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -579,7 +579,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -610,7 +610,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`original_image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`original_image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -643,7 +643,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`mask_image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`mask_image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -823,7 +823,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
image: Union[PIL.Image.Image, np.ndarray, torch.FloatTensor],
image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],
original_image: Union[
PIL.Image.Image, torch.Tensor, np.ndarray, List[PIL.Image.Image], List[torch.Tensor], List[np.ndarray]
] = None,
......@@ -839,11 +839,11 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
noise_level: int = 0,
......@@ -853,10 +853,10 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
Function invoked when calling the pipeline for generation.
Args:
image (`torch.FloatTensor` or `PIL.Image.Image`):
image (`torch.Tensor` or `PIL.Image.Image`):
`Image`, or tensor representing an image batch, that will be used as the starting point for the
process.
original_image (`torch.FloatTensor` or `PIL.Image.Image`):
original_image (`torch.Tensor` or `PIL.Image.Image`):
The original image that `image` was varied from.
mask_image (`PIL.Image.Image`):
`Image`, or tensor representing an image batch, to mask `image`. White pixels in the mask will be
......@@ -896,10 +896,10 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -910,7 +910,7 @@ class IFInpaintingSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
callback (`Callable`, *optional*):
A function that will be called every `callback_steps` steps during inference. The function will be
called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function will be called. If not specified, the callback will be
called at every step.
......
src/diffusers/pipelines/deepfloyd_if/pipeline_if_superresolution.py
View file @ be4afa0b
......@@ -298,8 +298,8 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: int = 1,
device: Optional[torch.device] = None,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
clean_caption: bool = False,
):
r"""
......@@ -318,10 +318,10 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -537,7 +537,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
and not isinstance(check_image_type, np.ndarray)
):
raise ValueError(
"`image` has to be of type `torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
"`image` has to be of type `torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, or List[...] but is"
f" {type(check_image_type)}"
)
......@@ -608,7 +608,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
prompt: Union[str, List[str]] = None,
height: int = None,
width: int = None,
image: Union[PIL.Image.Image, np.ndarray, torch.FloatTensor] = None,
image: Union[PIL.Image.Image, np.ndarray, torch.Tensor] = None,
num_inference_steps: int = 50,
timesteps: List[int] = None,
guidance_scale: float = 4.0,
......@@ -616,11 +616,11 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
noise_level: int = 250,
......@@ -637,7 +637,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
The height in pixels of the generated image.
width (`int`, *optional*, defaults to None):
The width in pixels of the generated image.
image (`PIL.Image.Image`, `np.ndarray`, `torch.FloatTensor`):
image (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`):
The image to be upscaled.
num_inference_steps (`int`, *optional*, defaults to 50):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
......@@ -663,10 +663,10 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
to make generation deterministic.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -677,7 +677,7 @@ class IFSuperResolutionPipeline(DiffusionPipeline, LoraLoaderMixin):
Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
callback (`Callable`, *optional*):
A function that will be called every `callback_steps` steps during inference. The function will be
called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
callback_steps (`int`, *optional*, defaults to 1):
The frequency at which the `callback` function will be called. If not specified, the callback will be
called at every step.
......
src/diffusers/pipelines/deprecated/alt_diffusion/modeling_roberta_series.py
View file @ be4afa0b
......@@ -13,27 +13,27 @@ class TransformationModelOutput(ModelOutput):
Base class for text model's outputs that also contains a pooling of the last hidden states.
Args:
text_embeds (`torch.FloatTensor` of shape `(batch_size, output_dim)` *optional* returned when model is initialized with `with_projection=True`):
text_embeds (`torch.Tensor` of shape `(batch_size, output_dim)` *optional* returned when model is initialized with `with_projection=True`):
The text embeddings obtained by applying the projection layer to the pooler_output.
last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
last_hidden_state (`torch.Tensor` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
hidden_states (`tuple(torch.Tensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `torch.Tensor` (one for the output of the embeddings, if the model has an embedding layer, + one
for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
attentions (`tuple(torch.Tensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `torch.Tensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
"""
projection_state: Optional[torch.FloatTensor] = None
last_hidden_state: torch.FloatTensor = None
hidden_states: Optional[Tuple[torch.FloatTensor]] = None
attentions: Optional[Tuple[torch.FloatTensor]] = None
projection_state: Optional[torch.Tensor] = None
last_hidden_state: torch.Tensor = None
hidden_states: Optional[Tuple[torch.Tensor]] = None
attentions: Optional[Tuple[torch.Tensor]] = None
class RobertaSeriesConfig(XLMRobertaConfig):
......
src/diffusers/pipelines/deprecated/alt_diffusion/pipeline_alt_diffusion.py
View file @ be4afa0b
......@@ -278,8 +278,8 @@ class AltDiffusionPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
**kwargs,
):
......@@ -310,8 +310,8 @@ class AltDiffusionPipeline(
num_images_per_prompt,
do_classifier_free_guidance,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
lora_scale: Optional[float] = None,
clip_skip: Optional[int] = None,
):
......@@ -331,10 +331,10 @@ class AltDiffusionPipeline(
The prompt or prompts not to guide the image generation. If not defined, one has to pass
`negative_prompt_embeds` instead. Ignored when not using guidance (i.e., ignored if `guidance_scale` is
less than `1`).
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
provided, text embeddings will be generated from `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
argument.
......@@ -637,7 +637,7 @@ class AltDiffusionPipeline(
data type of the generated embeddings
Returns:
`torch.FloatTensor`: Embedding vectors with shape `(len(timesteps), embedding_dim)`
`torch.Tensor`: Embedding vectors with shape `(len(timesteps), embedding_dim)`
"""
assert len(w.shape) == 1
w = w * 1000.0
......@@ -694,9 +694,9 @@ class AltDiffusionPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
ip_adapter_image: Optional[PipelineImageInput] = None,
output_type: Optional[str] = "pil",
return_dict: bool = True,
......@@ -738,14 +738,14 @@ class AltDiffusionPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor`, *optional*):
latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor is generated by sampling using the supplied random `generator`.
prompt_embeds (`torch.FloatTensor`, *optional*):
prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the `prompt` input argument.
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
negative_prompt_embeds (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided, `negative_prompt_embeds` are generated from the `negative_prompt` input argument.
ip_adapter_image: (`PipelineImageInput`, *optional*): Optional image input to work with IP Adapters.
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment