Skip to content

GitLab

"tests/pipelines/vscode:/vscode.git/clone" did not exist on "6ae7e8112a49ac20ade10ac639a76edbd9817a51"
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 218 additions and 218 deletions
src/diffusers/pipelines/semantic_stable_diffusion/pipeline_semantic_stable_diffusion.py
View file @ be4afa0b
......@@ -224,10 +224,10 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
num_images_per_prompt: int = 1,
eta: float = 0.0,
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,
editing_prompt: Optional[Union[str, List[str]]] = None,
editing_prompt_embeddings: Optional[torch.Tensor] = None,
......@@ -268,7 +268,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
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`.
......@@ -279,7 +279,7 @@ class SemanticStableDiffusionPipeline(DiffusionPipeline, StableDiffusionMixin):
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/shap_e/pipeline_shap_e.py
View file @ be4afa0b
......@@ -69,7 +69,7 @@ class ShapEPipelineOutput(BaseOutput):
Output class for [`ShapEPipeline`] and [`ShapEImg2ImgPipeline`].
Args:
images (`torch.FloatTensor`)
images (`torch.Tensor`)
A list of images for 3D rendering.
"""
......@@ -187,7 +187,7 @@ class ShapEPipeline(DiffusionPipeline):
num_images_per_prompt: int = 1,
num_inference_steps: int = 25,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
guidance_scale: float = 4.0,
frame_size: int = 64,
output_type: Optional[str] = "pil", # pil, np, latent, mesh
......@@ -207,7 +207,7 @@ class ShapEPipeline(DiffusionPipeline):
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`.
......
src/diffusers/pipelines/shap_e/pipeline_shap_e_img2img.py
View file @ be4afa0b
......@@ -70,7 +70,7 @@ class ShapEPipelineOutput(BaseOutput):
Output class for [`ShapEPipeline`] and [`ShapEImg2ImgPipeline`].
Args:
images (`torch.FloatTensor`)
images (`torch.Tensor`)
A list of images for 3D rendering.
"""
......@@ -169,7 +169,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
num_images_per_prompt: int = 1,
num_inference_steps: int = 25,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
guidance_scale: float = 4.0,
frame_size: int = 64,
output_type: Optional[str] = "pil", # pil, np, latent, mesh
......@@ -179,7 +179,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
The call function to the pipeline for generation.
Args:
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
`Image` or tensor representing an image batch to be used as the starting point. Can also accept image
latents as image, but if passing latents directly it is not encoded again.
num_images_per_prompt (`int`, *optional*, defaults to 1):
......@@ -190,7 +190,7 @@ class ShapEImg2ImgPipeline(DiffusionPipeline):
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`.
......
src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade.py
View file @ be4afa0b
......@@ -129,10 +129,10 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
do_classifier_free_guidance,
prompt=None,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
prompt_embeds_pooled: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
):
if prompt_embeds is None:
# get prompt text embeddings
......@@ -285,18 +285,18 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
image_embeddings: Union[torch.FloatTensor, List[torch.FloatTensor]],
image_embeddings: Union[torch.Tensor, List[torch.Tensor]],
prompt: Union[str, List[str]] = None,
num_inference_steps: int = 10,
guidance_scale: float = 0.0,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
prompt_embeds_pooled: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
num_images_per_prompt: int = 1,
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_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
......@@ -306,7 +306,7 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
Function invoked when calling the pipeline for generation.
Args:
image_embedding (`torch.FloatTensor` or `List[torch.FloatTensor]`):
image_embedding (`torch.Tensor` or `List[torch.Tensor]`):
Image Embeddings either extracted from an image or generated by a Prior Model.
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
......@@ -322,17 +322,17 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
negative_prompt (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
if `decoder_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.
prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
prompt_embeds_pooled (`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_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.
negative_prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
negative_prompt_embeds_pooled (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds_pooled will be generated from `negative_prompt`
input argument.
......@@ -341,7 +341,7 @@ class StableCascadeDecoderPipeline(DiffusionPipeline):
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`.
......
src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_combined.py
View file @ be4afa0b
......@@ -162,13 +162,13 @@ class StableCascadeCombinedPipeline(DiffusionPipeline):
num_inference_steps: int = 12,
decoder_guidance_scale: float = 0.0,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
prompt_embeds_pooled: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
num_images_per_prompt: int = 1,
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,
prior_callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
......@@ -187,17 +187,17 @@ class StableCascadeCombinedPipeline(DiffusionPipeline):
negative_prompt (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation. 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 for the prior. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, text embeddings will be generated from `prompt` input argument.
prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
prompt_embeds_pooled (`torch.Tensor`, *optional*):
Pre-generated text embeddings for the prior. 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 for the prior. 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.
negative_prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
negative_prompt_embeds_pooled (`torch.Tensor`, *optional*):
Pre-generated negative text embeddings for the prior. 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.
......@@ -230,7 +230,7 @@ class StableCascadeCombinedPipeline(DiffusionPipeline):
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`.
......
src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_prior.py
View file @ be4afa0b
......@@ -54,19 +54,19 @@ class StableCascadePriorPipelineOutput(BaseOutput):
Output class for WuerstchenPriorPipeline.
Args:
image_embeddings (`torch.FloatTensor` or `np.ndarray`)
image_embeddings (`torch.Tensor` or `np.ndarray`)
Prior image embeddings for text prompt
prompt_embeds (`torch.FloatTensor`):
prompt_embeds (`torch.Tensor`):
Text embeddings for the prompt.
negative_prompt_embeds (`torch.FloatTensor`):
negative_prompt_embeds (`torch.Tensor`):
Text embeddings for the negative prompt.
"""
image_embeddings: Union[torch.FloatTensor, np.ndarray]
prompt_embeds: Union[torch.FloatTensor, np.ndarray]
prompt_embeds_pooled: Union[torch.FloatTensor, np.ndarray]
negative_prompt_embeds: Union[torch.FloatTensor, np.ndarray]
negative_prompt_embeds_pooled: Union[torch.FloatTensor, np.ndarray]
image_embeddings: Union[torch.Tensor, np.ndarray]
prompt_embeds: Union[torch.Tensor, np.ndarray]
prompt_embeds_pooled: Union[torch.Tensor, np.ndarray]
negative_prompt_embeds: Union[torch.Tensor, np.ndarray]
negative_prompt_embeds_pooled: Union[torch.Tensor, np.ndarray]
class StableCascadePriorPipeline(DiffusionPipeline):
......@@ -150,10 +150,10 @@ class StableCascadePriorPipeline(DiffusionPipeline):
do_classifier_free_guidance,
prompt=None,
negative_prompt=None,
prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
prompt_embeds_pooled: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
):
if prompt_embeds is None:
# get prompt text embeddings
......@@ -374,14 +374,14 @@ class StableCascadePriorPipeline(DiffusionPipeline):
timesteps: List[float] = None,
guidance_scale: float = 4.0,
negative_prompt: Optional[Union[str, List[str]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
negative_prompt_embeds: Optional[torch.FloatTensor] = None,
negative_prompt_embeds_pooled: Optional[torch.FloatTensor] = None,
image_embeds: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
prompt_embeds_pooled: Optional[torch.Tensor] = None,
negative_prompt_embeds: Optional[torch.Tensor] = None,
negative_prompt_embeds_pooled: Optional[torch.Tensor] = None,
image_embeds: Optional[torch.Tensor] = None,
num_images_per_prompt: Optional[int] = 1,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pt",
return_dict: bool = True,
callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
......@@ -409,21 +409,21 @@ class StableCascadePriorPipeline(DiffusionPipeline):
negative_prompt (`str` or `List[str]`, *optional*):
The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
if `decoder_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.
prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
prompt_embeds_pooled (`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_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.
negative_prompt_embeds_pooled (`torch.FloatTensor`, *optional*):
negative_prompt_embeds_pooled (`torch.Tensor`, *optional*):
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
weighting. If not provided, negative_prompt_embeds_pooled will be generated from `negative_prompt`
input argument.
image_embeds (`torch.FloatTensor`, *optional*):
image_embeds (`torch.Tensor`, *optional*):
Pre-generated image embeddings. Can be used to easily tweak image inputs, *e.g.* prompt weighting. If
not provided, image embeddings will be generated from `image` input argument if existing.
num_images_per_prompt (`int`, *optional*, defaults to 1):
......@@ -431,7 +431,7 @@ class StableCascadePriorPipeline(DiffusionPipeline):
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`.
......
src/diffusers/pipelines/stable_diffusion/pipeline_onnx_stable_diffusion.py
View file @ be4afa0b
......@@ -288,7 +288,7 @@ class OnnxStableDiffusionPipeline(DiffusionPipeline):
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 (`PIL.Image.Image` or List[`PIL.Image.Image`] or `torch.FloatTensor`):
image (`PIL.Image.Image` or List[`PIL.Image.Image`] or `torch.Tensor`):
`Image`, or tensor representing an image batch which will 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
......@@ -329,7 +329,7 @@ class OnnxStableDiffusionPipeline(DiffusionPipeline):
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/stable_diffusion/pipeline_onnx_stable_diffusion_upscale.py
View file @ be4afa0b
......@@ -395,7 +395,7 @@ class OnnxStableDiffusionUpscalePipeline(DiffusionPipeline):
[`schedulers.DDIMScheduler`], will be ignored for others.
generator (`np.random.RandomState`, *optional*):
A np.random.RandomState 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/stable_diffusion/pipeline_stable_diffusion.py
View file @ be4afa0b
......@@ -274,8 +274,8 @@ class StableDiffusionPipeline(
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,
):
......@@ -306,8 +306,8 @@ class StableDiffusionPipeline(
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,
):
......@@ -327,10 +327,10 @@ class StableDiffusionPipeline(
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.
......@@ -691,7 +691,7 @@ class StableDiffusionPipeline(
# 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
......@@ -704,7 +704,7 @@ class StableDiffusionPipeline(
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
......@@ -765,11 +765,11 @@ class StableDiffusionPipeline(
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,
......@@ -814,18 +814,18 @@ class StableDiffusionPipeline(
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/stable_diffusion/pipeline_stable_diffusion_depth2img.py
View file @ be4afa0b
......@@ -156,8 +156,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
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,
):
......@@ -189,8 +189,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
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,
):
......@@ -210,10 +210,10 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
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.
......@@ -609,7 +609,7 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
self,
prompt: Union[str, List[str]] = None,
image: PipelineImageInput = None,
depth_map: Optional[torch.FloatTensor] = None,
depth_map: Optional[torch.Tensor] = None,
strength: float = 0.8,
num_inference_steps: Optional[int] = 50,
guidance_scale: Optional[float] = 7.5,
......@@ -617,8 +617,8 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
num_images_per_prompt: Optional[int] = 1,
eta: Optional[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,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
......@@ -633,10 +633,10 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
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]`, or `List[np.ndarray]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
`Image` or tensor representing an image batch to be used as the starting point. Can accept image
latents as `image` only if `depth_map` is not `None`.
depth_map (`torch.FloatTensor`, *optional*):
depth_map (`torch.Tensor`, *optional*):
Depth prediction to be used as additional conditioning for the image generation process. If not
defined, it automatically predicts the depth with `self.depth_estimator`.
strength (`float`, *optional*, defaults to 0.8):
......@@ -662,10 +662,10 @@ class StableDiffusionDepth2ImgPipeline(DiffusionPipeline, TextualInversionLoader
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](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 (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/stable_diffusion/pipeline_stable_diffusion_image_variation.py
View file @ be4afa0b
......@@ -207,7 +207,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
and not isinstance(image, list)
):
raise ValueError(
"`image` has to be of type `torch.FloatTensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
"`image` has to be of type `torch.Tensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
f" {type(image)}"
)
......@@ -248,7 +248,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
@torch.no_grad()
def __call__(
self,
image: Union[PIL.Image.Image, List[PIL.Image.Image], torch.FloatTensor],
image: Union[PIL.Image.Image, List[PIL.Image.Image], torch.Tensor],
height: Optional[int] = None,
width: Optional[int] = None,
num_inference_steps: int = 50,
......@@ -256,17 +256,17 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
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,
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"""
The call function to the pipeline for generation.
Args:
image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `torch.FloatTensor`):
image (`PIL.Image.Image` or `List[PIL.Image.Image]` or `torch.Tensor`):
Image or images to guide image generation. If you provide a tensor, it needs to be compatible with
[`CLIPImageProcessor`](https://huggingface.co/lambdalabs/sd-image-variations-diffusers/blob/main/feature_extractor/preprocessor_config.json).
height (`int`, *optional*, defaults to `self.unet.config.sample_size * self.vae_scale_factor`):
......@@ -287,7 +287,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
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`.
......@@ -298,7 +298,7 @@ class StableDiffusionImageVariationPipeline(DiffusionPipeline, StableDiffusionMi
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/stable_diffusion/pipeline_stable_diffusion_img2img.py
View file @ be4afa0b
......@@ -315,8 +315,8 @@ class StableDiffusionImg2ImgPipeline(
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,
):
......@@ -348,8 +348,8 @@ class StableDiffusionImg2ImgPipeline(
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,
):
......@@ -369,10 +369,10 @@ class StableDiffusionImg2ImgPipeline(
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.
......@@ -784,7 +784,7 @@ class StableDiffusionImg2ImgPipeline(
# 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
......@@ -797,7 +797,7 @@ class StableDiffusionImg2ImgPipeline(
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
......@@ -854,10 +854,10 @@ class StableDiffusionImg2ImgPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: Optional[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,
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,
......@@ -872,7 +872,7 @@ class StableDiffusionImg2ImgPipeline(
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]`, or `List[np.ndarray]`):
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
......@@ -909,14 +909,14 @@ class StableDiffusionImg2ImgPipeline(
generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
A [`torch.Generator`](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 (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/stable_diffusion/pipeline_stable_diffusion_inpaint.py
View file @ be4afa0b
......@@ -387,8 +387,8 @@ class StableDiffusionInpaintPipeline(
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,
):
......@@ -420,8 +420,8 @@ class StableDiffusionInpaintPipeline(
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,
):
......@@ -441,10 +441,10 @@ class StableDiffusionInpaintPipeline(
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.
......@@ -931,7 +931,7 @@ class StableDiffusionInpaintPipeline(
# 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
......@@ -944,7 +944,7 @@ class StableDiffusionInpaintPipeline(
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
......@@ -992,7 +992,7 @@ class StableDiffusionInpaintPipeline(
prompt: Union[str, List[str]] = None,
image: PipelineImageInput = None,
mask_image: PipelineImageInput = None,
masked_image_latents: torch.FloatTensor = None,
masked_image_latents: torch.Tensor = None,
height: Optional[int] = None,
width: Optional[int] = None,
padding_mask_crop: Optional[int] = None,
......@@ -1005,11 +1005,11 @@ class StableDiffusionInpaintPipeline(
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,
......@@ -1024,14 +1024,14 @@ class StableDiffusionInpaintPipeline(
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]`, or `List[np.ndarray]`):
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 inpainted (which parts of the image to
be masked out with `mask_image` and repainted according to `prompt`). 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]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
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
single channel (luminance) before use. If it's a numpy array or pytorch tensor, it should contain one
......@@ -1080,18 +1080,18 @@ class StableDiffusionInpaintPipeline(
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/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py
View file @ be4afa0b
......@@ -168,11 +168,11 @@ class StableDiffusionInstructPix2PixPipeline(
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,
callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
......@@ -185,7 +185,7 @@ class StableDiffusionInstructPix2PixPipeline(
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` `np.ndarray`, `PIL.Image.Image`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
image (`torch.Tensor` `np.ndarray`, `PIL.Image.Image`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
`Image` or tensor representing an image batch to be repainted according to `prompt`. Can also accept
image latents as `image`, but if passing latents directly it is not encoded again.
num_inference_steps (`int`, *optional*, defaults to 100):
......@@ -210,14 +210,14 @@ class StableDiffusionInstructPix2PixPipeline(
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`.
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*):
......@@ -471,8 +471,8 @@ class StableDiffusionInstructPix2PixPipeline(
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,
):
r"""
Encodes the prompt into text encoder hidden states.
......@@ -490,10 +490,10 @@ class StableDiffusionInstructPix2PixPipeline(
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.
......
src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_latent_upscale.py
View file @ be4afa0b
......@@ -267,10 +267,10 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
guidance_scale: float = 9.0,
negative_prompt: Optional[Union[str, List[str]]] = 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"""
......@@ -279,7 +279,7 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide image upscaling.
image (`torch.FloatTensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.FloatTensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
`Image` or tensor representing an image batch to be upscaled. If it's a tensor, it can be either a
latent output from a Stable Diffusion model or an image tensor in the range `[-1, 1]`. It is considered
a `latent` if `image.shape[1]` is `4`; otherwise, it is considered to be an image representation and
......@@ -299,7 +299,7 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
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`.
......@@ -310,7 +310,7 @@ class StableDiffusionLatentUpscalePipeline(DiffusionPipeline, StableDiffusionMix
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/stable_diffusion/pipeline_stable_diffusion_upscale.py
View file @ be4afa0b
......@@ -176,8 +176,8 @@ class StableDiffusionUpscalePipeline(
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,
):
......@@ -209,8 +209,8 @@ class StableDiffusionUpscalePipeline(
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,
):
......@@ -230,10 +230,10 @@ class StableDiffusionUpscalePipeline(
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.
......@@ -542,12 +542,12 @@ class StableDiffusionUpscalePipeline(
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,
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,
clip_skip: int = None,
......@@ -558,7 +558,7 @@ class StableDiffusionUpscalePipeline(
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]`, or `List[np.ndarray]`):
image (`torch.Tensor`, `PIL.Image.Image`, `np.ndarray`, `List[torch.Tensor]`, `List[PIL.Image.Image]`, or `List[np.ndarray]`):
`Image` or tensor representing an image batch 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
......@@ -577,14 +577,14 @@ class StableDiffusionUpscalePipeline(
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"`):
......@@ -594,7 +594,7 @@ class StableDiffusionUpscalePipeline(
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/stable_diffusion/pipeline_stable_unclip.py
View file @ be4afa0b
......@@ -257,8 +257,8 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
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,
):
......@@ -290,8 +290,8 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
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,
):
......@@ -311,10 +311,10 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
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.
......@@ -588,7 +588,7 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
self,
image_embeds: torch.Tensor,
noise_level: int,
noise: Optional[torch.FloatTensor] = None,
noise: Optional[torch.Tensor] = None,
generator: Optional[torch.Generator] = None,
):
"""
......@@ -644,19 +644,19 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[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,
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,
# prior args
prior_num_inference_steps: int = 25,
prior_guidance_scale: float = 4.0,
prior_latents: Optional[torch.FloatTensor] = None,
prior_latents: Optional[torch.Tensor] = None,
clip_skip: Optional[int] = None,
):
"""
......@@ -686,14 +686,14 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
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"`):
......@@ -702,7 +702,7 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
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.
......@@ -718,7 +718,7 @@ class StableUnCLIPPipeline(DiffusionPipeline, StableDiffusionMixin, TextualInver
prior_guidance_scale (`float`, *optional*, defaults to 4.0):
A higher guidance scale value encourages the model to generate images closely linked to the text
`prompt` at the expense of lower image quality. Guidance scale is enabled when `guidance_scale > 1`.
prior_latents (`torch.FloatTensor`, *optional*):
prior_latents (`torch.Tensor`, *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
embedding generation in the prior denoising process. 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
......
src/diffusers/pipelines/stable_diffusion/pipeline_stable_unclip_img2img.py
View file @ be4afa0b
......@@ -166,8 +166,8 @@ class StableUnCLIPImg2ImgPipeline(
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,
):
......@@ -254,8 +254,8 @@ class StableUnCLIPImg2ImgPipeline(
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,
):
......@@ -275,10 +275,10 @@ class StableUnCLIPImg2ImgPipeline(
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.
......@@ -537,7 +537,7 @@ class StableUnCLIPImg2ImgPipeline(
and not isinstance(image, list)
):
raise ValueError(
"`image` has to be of type `torch.FloatTensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
"`image` has to be of type `torch.Tensor` or `PIL.Image.Image` or `List[PIL.Image.Image]` but is"
f" {type(image)}"
)
......@@ -569,7 +569,7 @@ class StableUnCLIPImg2ImgPipeline(
self,
image_embeds: torch.Tensor,
noise_level: int,
noise: Optional[torch.FloatTensor] = None,
noise: Optional[torch.Tensor] = None,
generator: Optional[torch.Generator] = None,
):
"""
......@@ -615,7 +615,7 @@ class StableUnCLIPImg2ImgPipeline(
@replace_example_docstring(EXAMPLE_DOC_STRING)
def __call__(
self,
image: Union[torch.FloatTensor, PIL.Image.Image] = None,
image: Union[torch.Tensor, PIL.Image.Image] = None,
prompt: Union[str, List[str]] = None,
height: Optional[int] = None,
width: Optional[int] = None,
......@@ -625,16 +625,16 @@ class StableUnCLIPImg2ImgPipeline(
num_images_per_prompt: Optional[int] = 1,
eta: float = 0.0,
generator: Optional[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,
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,
image_embeds: Optional[torch.FloatTensor] = None,
image_embeds: Optional[torch.Tensor] = None,
clip_skip: Optional[int] = None,
):
r"""
......@@ -644,7 +644,7 @@ class StableUnCLIPImg2ImgPipeline(
prompt (`str` or `List[str]`, *optional*):
The prompt or prompts to guide the image generation. If not defined, either `prompt_embeds` will be
used or prompt is initialized to `""`.
image (`torch.FloatTensor` or `PIL.Image.Image`):
image (`torch.Tensor` or `PIL.Image.Image`):
`Image` or tensor representing an image batch. The image is encoded to its CLIP embedding which the
`unet` is conditioned on. The image is _not_ encoded by the `vae` and then used as the latents in the
denoising process like it is in the standard Stable Diffusion text-guided image variation process.
......@@ -669,14 +669,14 @@ class StableUnCLIPImg2ImgPipeline(
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"`):
......@@ -685,7 +685,7 @@ class StableUnCLIPImg2ImgPipeline(
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.
......@@ -695,7 +695,7 @@ class StableUnCLIPImg2ImgPipeline(
noise_level (`int`, *optional*, defaults to `0`):
The amount of noise to add to the image embeddings. A higher `noise_level` increases the variance in
the final un-noised images. See [`StableUnCLIPPipeline.noise_image_embeddings`] for more details.
image_embeds (`torch.FloatTensor`, *optional*):
image_embeds (`torch.Tensor`, *optional*):
Pre-generated CLIP embeddings to condition the `unet` on. These latents are not used in the denoising
process. If you want to provide pre-generated latents, pass them to `__call__` as `latents`.
clip_skip (`int`, *optional*):
......
src/diffusers/pipelines/stable_diffusion/safety_checker.py
View file @ be4afa0b
......@@ -100,7 +100,7 @@ class StableDiffusionSafetyChecker(PreTrainedModel):
return images, has_nsfw_concepts
@torch.no_grad()
def forward_onnx(self, clip_input: torch.FloatTensor, images: torch.FloatTensor):
def forward_onnx(self, clip_input: torch.Tensor, images: torch.Tensor):
pooled_output = self.vision_model(clip_input)[1] # pooled_output
image_embeds = self.visual_projection(pooled_output)
......
src/diffusers/pipelines/stable_diffusion_attend_and_excite/pipeline_stable_diffusion_attend_and_excite.py
View file @ be4afa0b
......@@ -254,8 +254,8 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
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,
):
......@@ -287,8 +287,8 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
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,
):
......@@ -308,10 +308,10 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
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.
......@@ -746,12 +746,12 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
num_images_per_prompt: 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,
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,
max_iter_to_alter: int = 25,
......@@ -789,14 +789,14 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
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"`):
......@@ -806,7 +806,7 @@ class StableDiffusionAttendAndExcitePipeline(DiffusionPipeline, StableDiffusionM
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.
......
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