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
Show whitespace changes
Inline Side-by-side
Showing with 237 additions and 237 deletions
src/diffusers/pipelines/deprecated/alt_diffusion/pipeline_alt_diffusion_img2img.py
View file @ be4afa0b
......@@ -318,8 +318,8 @@ class AltDiffusionImg2ImgPipeline(
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,
):
......@@ -350,8 +350,8 @@ class AltDiffusionImg2ImgPipeline(
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,
):
......@@ -371,10 +371,10 @@ class AltDiffusionImg2ImgPipeline(
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.
......@@ -721,7 +721,7 @@ class AltDiffusionImg2ImgPipeline(
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
......@@ -774,8 +774,8 @@ class AltDiffusionImg2ImgPipeline(
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,
output_type: Optional[str] = "pil",
return_dict: bool = True,
......@@ -791,7 +791,7 @@ class AltDiffusionImg2ImgPipeline(
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
......@@ -824,10 +824,10 @@ class AltDiffusionImg2ImgPipeline(
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.
......
src/diffusers/pipelines/deprecated/repaint/pipeline_repaint.py
View file @ be4afa0b
......@@ -112,9 +112,9 @@ class RePaintPipeline(DiffusionPipeline):
The call function to the pipeline for generation.
Args:
image (`torch.FloatTensor` or `PIL.Image.Image`):
image (`torch.Tensor` or `PIL.Image.Image`):
The original image to inpaint on.
mask_image (`torch.FloatTensor` or `PIL.Image.Image`):
mask_image (`torch.Tensor` or `PIL.Image.Image`):
The mask_image where 0.0 define which part of the original image to inpaint.
num_inference_steps (`int`, *optional*, defaults to 1000):
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
......
src/diffusers/pipelines/deprecated/spectrogram_diffusion/pipeline_spectrogram_diffusion.py
View file @ be4afa0b
......@@ -134,7 +134,7 @@ class SpectrogramDiffusionPipeline(DiffusionPipeline):
num_inference_steps: int = 100,
return_dict: bool = True,
output_type: str = "np",
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
) -> Union[AudioPipelineOutput, Tuple]:
if (callback_steps is None) or (
......@@ -161,7 +161,7 @@ class SpectrogramDiffusionPipeline(DiffusionPipeline):
The output format of the generated audio.
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/deprecated/stable_diffusion_variants/pipeline_cycle_diffusion.py
View file @ be4afa0b
......@@ -255,8 +255,8 @@ class CycleDiffusionPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
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,
):
......@@ -288,8 +288,8 @@ class CycleDiffusionPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
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,
):
......@@ -309,10 +309,10 @@ class CycleDiffusionPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
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.
......@@ -638,10 +638,10 @@ class CycleDiffusionPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
num_images_per_prompt: Optional[int] = 1,
eta: Optional[float] = 0.1,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
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: Optional[int] = None,
......@@ -652,7 +652,7 @@ class CycleDiffusionPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
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 used as the starting point. Can also accept image
latents as `image`, but if passing latents directly it is not encoded again.
strength (`float`, *optional*, defaults to 0.8):
......@@ -678,10 +678,10 @@ class CycleDiffusionPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
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"`):
......@@ -691,7 +691,7 @@ class CycleDiffusionPipeline(DiffusionPipeline, TextualInversionLoaderMixin, Lor
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/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_inpaint_legacy.py
View file @ be4afa0b
......@@ -48,7 +48,7 @@ def preprocess_image(image, batch_size):
def preprocess_mask(mask, batch_size, scale_factor=8):
if not isinstance(mask, torch.FloatTensor):
if not isinstance(mask, torch.Tensor):
mask = mask.convert("L")
w, h = mask.size
w, h = (x - x % 8 for x in (w, h)) # resize to integer multiple of 8
......@@ -225,8 +225,8 @@ class StableDiffusionInpaintPipelineLegacy(
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,
):
......@@ -258,8 +258,8 @@ class StableDiffusionInpaintPipelineLegacy(
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,
):
......@@ -279,10 +279,10 @@ class StableDiffusionInpaintPipelineLegacy(
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.
......@@ -557,8 +557,8 @@ class StableDiffusionInpaintPipelineLegacy(
def __call__(
self,
prompt: Union[str, List[str]] = None,
image: Union[torch.FloatTensor, PIL.Image.Image] = None,
mask_image: Union[torch.FloatTensor, PIL.Image.Image] = None,
image: Union[torch.Tensor, PIL.Image.Image] = None,
mask_image: Union[torch.Tensor, PIL.Image.Image] = None,
strength: float = 0.8,
num_inference_steps: Optional[int] = 50,
guidance_scale: Optional[float] = 7.5,
......@@ -567,11 +567,11 @@ class StableDiffusionInpaintPipelineLegacy(
add_predicted_noise: Optional[bool] = False,
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,
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: Optional[int] = None,
......@@ -583,10 +583,10 @@ class StableDiffusionInpaintPipelineLegacy(
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. This is the image whose masked region will be inpainted.
mask_image (`torch.FloatTensor` or `PIL.Image.Image`):
mask_image (`torch.Tensor` or `PIL.Image.Image`):
`Image`, or tensor representing an image batch, to mask `image`. White pixels in the mask will be
replaced by noise and therefore repainted, while black pixels will be preserved. If `mask_image` is a
PIL image, it will be converted to a single channel (luminance) before use. If mask is a tensor, the
......@@ -620,10 +620,10 @@ class StableDiffusionInpaintPipelineLegacy(
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.
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.
......@@ -635,7 +635,7 @@ class StableDiffusionInpaintPipelineLegacy(
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.
......@@ -693,7 +693,7 @@ class StableDiffusionInpaintPipelineLegacy(
prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
# 4. Preprocess image and mask
if not isinstance(image, torch.FloatTensor):
if not isinstance(image, torch.Tensor):
image = preprocess_image(image, batch_size)
mask_image = preprocess_mask(mask_image, batch_size, self.vae_scale_factor)
......
src/diffusers/pipelines/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_model_editing.py
View file @ be4afa0b
......@@ -163,8 +163,8 @@ class StableDiffusionModelEditingPipeline(
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,
):
......@@ -196,8 +196,8 @@ class StableDiffusionModelEditingPipeline(
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,
):
......@@ -217,10 +217,10 @@ class StableDiffusionModelEditingPipeline(
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.
......@@ -620,12 +620,12 @@ class StableDiffusionModelEditingPipeline(
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: Optional[int] = None,
......@@ -657,14 +657,14 @@ class StableDiffusionModelEditingPipeline(
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"`):
......@@ -674,7 +674,7 @@ class StableDiffusionModelEditingPipeline(
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/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_paradigms.py
View file @ be4afa0b
......@@ -154,8 +154,8 @@ class StableDiffusionParadigmsPipeline(
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,
):
......@@ -187,8 +187,8 @@ class StableDiffusionParadigmsPipeline(
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,
):
......@@ -208,10 +208,10 @@ class StableDiffusionParadigmsPipeline(
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.
......@@ -492,12 +492,12 @@ class StableDiffusionParadigmsPipeline(
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,
debug: bool = False,
......@@ -537,14 +537,14 @@ class StableDiffusionParadigmsPipeline(
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"`):
......@@ -554,7 +554,7 @@ class StableDiffusionParadigmsPipeline(
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/deprecated/stable_diffusion_variants/pipeline_stable_diffusion_pix2pix_zero.py
View file @ be4afa0b
......@@ -60,14 +60,14 @@ class Pix2PixInversionPipelineOutput(BaseOutput, TextualInversionLoaderMixin):
Output class for Stable Diffusion pipelines.
Args:
latents (`torch.FloatTensor`)
latents (`torch.Tensor`)
inverted latents tensor
images (`List[PIL.Image.Image]` or `np.ndarray`)
List of denoised PIL images of length `batch_size` or numpy array of shape `(batch_size, height, width,
num_channels)`. PIL images or numpy array present the denoised images of the diffusion pipeline.
"""
latents: torch.FloatTensor
latents: torch.Tensor
images: Union[List[PIL.Image.Image], np.ndarray]
......@@ -377,8 +377,8 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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,
):
......@@ -410,8 +410,8 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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,
):
......@@ -431,10 +431,10 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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.
......@@ -707,7 +707,7 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
return (embs_target.mean(0) - embs_source.mean(0)).unsqueeze(0)
@torch.no_grad()
def get_embeds(self, prompt: List[str], batch_size: int = 16) -> torch.FloatTensor:
def get_embeds(self, prompt: List[str], batch_size: int = 16) -> torch.Tensor:
num_prompts = len(prompt)
embeds = []
for i in range(0, num_prompts, batch_size):
......@@ -827,13 +827,13 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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,
cross_attention_guidance_amount: float = 0.1,
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: Optional[int] = 1,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
clip_skip: Optional[int] = None,
......@@ -876,14 +876,14 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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.
......@@ -897,7 +897,7 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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.
......@@ -1112,12 +1112,12 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
num_inference_steps: int = 50,
guidance_scale: float = 1,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
prompt_embeds: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
prompt_embeds: Optional[torch.Tensor] = None,
cross_attention_guidance_amount: float = 0.1,
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: Optional[int] = 1,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
lambda_auto_corr: float = 20.0,
......@@ -1132,7 +1132,7 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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` `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 which will be used for conditioning. Can also accept
image latents as `image`, if passing latents directly, it will not be encoded again.
num_inference_steps (`int`, *optional*, defaults to 50):
......@@ -1147,11 +1147,11 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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.
cross_attention_guidance_amount (`float`, defaults to 0.1):
......@@ -1164,7 +1164,7 @@ class StableDiffusionPix2PixZeroPipeline(DiffusionPipeline, StableDiffusionMixin
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/versatile_diffusion/modeling_text_unet.py
View file @ be4afa0b
......@@ -1048,7 +1048,7 @@ class UNetFlatConditionModel(ModelMixin, ConfigMixin):
def forward(
self,
sample: torch.FloatTensor,
sample: torch.Tensor,
timestep: Union[torch.Tensor, float, int],
encoder_hidden_states: torch.Tensor,
class_labels: Optional[torch.Tensor] = None,
......@@ -1066,10 +1066,10 @@ class UNetFlatConditionModel(ModelMixin, ConfigMixin):
The [`UNetFlatConditionModel`] forward method.
Args:
sample (`torch.FloatTensor`):
sample (`torch.Tensor`):
The noisy input tensor with the following shape `(batch, channel, height, width)`.
timestep (`torch.FloatTensor` or `float` or `int`): The number of timesteps to denoise an input.
encoder_hidden_states (`torch.FloatTensor`):
timestep (`torch.Tensor` or `float` or `int`): The number of timesteps to denoise an input.
encoder_hidden_states (`torch.Tensor`):
The encoder hidden states with shape `(batch, sequence_length, feature_dim)`.
class_labels (`torch.Tensor`, *optional*, defaults to `None`):
Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings.
......@@ -1590,8 +1590,8 @@ class DownBlockFlat(nn.Module):
self.gradient_checkpointing = False
def forward(
self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None
) -> Tuple[torch.FloatTensor, Tuple[torch.FloatTensor, ...]]:
self, hidden_states: torch.Tensor, temb: Optional[torch.Tensor] = None
) -> Tuple[torch.Tensor, Tuple[torch.Tensor, ...]]:
output_states = ()
for resnet in self.resnets:
......@@ -1719,14 +1719,14 @@ class CrossAttnDownBlockFlat(nn.Module):
def forward(
self,
hidden_states: torch.FloatTensor,
temb: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
attention_mask: Optional[torch.FloatTensor] = None,
hidden_states: torch.Tensor,
temb: Optional[torch.Tensor] = None,
encoder_hidden_states: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
additional_residuals: Optional[torch.FloatTensor] = None,
) -> Tuple[torch.FloatTensor, Tuple[torch.FloatTensor, ...]]:
encoder_attention_mask: Optional[torch.Tensor] = None,
additional_residuals: Optional[torch.Tensor] = None,
) -> Tuple[torch.Tensor, Tuple[torch.Tensor, ...]]:
output_states = ()
blocks = list(zip(self.resnets, self.attentions))
......@@ -1837,13 +1837,13 @@ class UpBlockFlat(nn.Module):
def forward(
self,
hidden_states: torch.FloatTensor,
res_hidden_states_tuple: Tuple[torch.FloatTensor, ...],
temb: Optional[torch.FloatTensor] = None,
hidden_states: torch.Tensor,
res_hidden_states_tuple: Tuple[torch.Tensor, ...],
temb: Optional[torch.Tensor] = None,
upsample_size: Optional[int] = None,
*args,
**kwargs,
) -> torch.FloatTensor:
) -> torch.Tensor:
if len(args) > 0 or kwargs.get("scale", None) is not None:
deprecation_message = "The `scale` argument is deprecated and will be ignored. Please remove it, as passing it will raise an error in the future. `scale` should directly be passed while calling the underlying pipeline component i.e., via `cross_attention_kwargs`."
deprecate("scale", "1.0.0", deprecation_message)
......@@ -1994,15 +1994,15 @@ class CrossAttnUpBlockFlat(nn.Module):
def forward(
self,
hidden_states: torch.FloatTensor,
res_hidden_states_tuple: Tuple[torch.FloatTensor, ...],
temb: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
hidden_states: torch.Tensor,
res_hidden_states_tuple: Tuple[torch.Tensor, ...],
temb: Optional[torch.Tensor] = None,
encoder_hidden_states: Optional[torch.Tensor] = None,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
upsample_size: Optional[int] = None,
attention_mask: Optional[torch.FloatTensor] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
) -> torch.FloatTensor:
attention_mask: Optional[torch.Tensor] = None,
encoder_attention_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
if cross_attention_kwargs is not None:
if cross_attention_kwargs.get("scale", None) is not None:
logger.warning("Passing `scale` to `cross_attention_kwargs` is deprecated. `scale` will be ignored.")
......@@ -2104,8 +2104,8 @@ class UNetMidBlockFlat(nn.Module):
output_scale_factor (`float`, *optional*, defaults to 1.0): The output scale factor.
Returns:
`torch.FloatTensor`: The output of the last residual block, which is a tensor of shape `(batch_size,
in_channels, height, width)`.
`torch.Tensor`: The output of the last residual block, which is a tensor of shape `(batch_size, in_channels,
height, width)`.
"""
......@@ -2223,7 +2223,7 @@ class UNetMidBlockFlat(nn.Module):
self.attentions = nn.ModuleList(attentions)
self.resnets = nn.ModuleList(resnets)
def forward(self, hidden_states: torch.FloatTensor, temb: Optional[torch.FloatTensor] = None) -> torch.FloatTensor:
def forward(self, hidden_states: torch.Tensor, temb: Optional[torch.Tensor] = None) -> torch.Tensor:
hidden_states = self.resnets[0](hidden_states, temb)
for attn, resnet in zip(self.attentions, self.resnets[1:]):
if attn is not None:
......@@ -2339,13 +2339,13 @@ class UNetMidBlockFlatCrossAttn(nn.Module):
def forward(
self,
hidden_states: torch.FloatTensor,
temb: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
attention_mask: Optional[torch.FloatTensor] = None,
hidden_states: torch.Tensor,
temb: Optional[torch.Tensor] = None,
encoder_hidden_states: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
) -> torch.FloatTensor:
encoder_attention_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
if cross_attention_kwargs is not None:
if cross_attention_kwargs.get("scale", None) is not None:
logger.warning("Passing `scale` to `cross_attention_kwargs` is deprecated. `scale` will be ignored.")
......@@ -2480,13 +2480,13 @@ class UNetMidBlockFlatSimpleCrossAttn(nn.Module):
def forward(
self,
hidden_states: torch.FloatTensor,
temb: Optional[torch.FloatTensor] = None,
encoder_hidden_states: Optional[torch.FloatTensor] = None,
attention_mask: Optional[torch.FloatTensor] = None,
hidden_states: torch.Tensor,
temb: Optional[torch.Tensor] = None,
encoder_hidden_states: Optional[torch.Tensor] = None,
attention_mask: Optional[torch.Tensor] = None,
cross_attention_kwargs: Optional[Dict[str, Any]] = None,
encoder_attention_mask: Optional[torch.FloatTensor] = None,
) -> torch.FloatTensor:
encoder_attention_mask: Optional[torch.Tensor] = None,
) -> torch.Tensor:
cross_attention_kwargs = cross_attention_kwargs if cross_attention_kwargs is not None else {}
if cross_attention_kwargs.get("scale", None) is not None:
logger.warning("Passing `scale` to `cross_attention_kwargs` is deprecated. `scale` will be ignored.")
......
src/diffusers/pipelines/deprecated/versatile_diffusion/pipeline_versatile_diffusion.py
View file @ be4afa0b
......@@ -81,7 +81,7 @@ class VersatileDiffusionPipeline(DiffusionPipeline):
@torch.no_grad()
def image_variation(
self,
image: Union[torch.FloatTensor, PIL.Image.Image],
image: Union[torch.Tensor, PIL.Image.Image],
height: Optional[int] = None,
width: Optional[int] = None,
num_inference_steps: int = 50,
......@@ -90,10 +90,10 @@ class VersatileDiffusionPipeline(DiffusionPipeline):
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"""
......@@ -123,7 +123,7 @@ class VersatileDiffusionPipeline(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`.
......@@ -134,7 +134,7 @@ class VersatileDiffusionPipeline(DiffusionPipeline):
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.
......@@ -202,10 +202,10 @@ class VersatileDiffusionPipeline(DiffusionPipeline):
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"""
......@@ -235,7 +235,7 @@ class VersatileDiffusionPipeline(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`.
......@@ -246,7 +246,7 @@ class VersatileDiffusionPipeline(DiffusionPipeline):
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.
......@@ -311,10 +311,10 @@ class VersatileDiffusionPipeline(DiffusionPipeline):
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"""
......@@ -344,7 +344,7 @@ class VersatileDiffusionPipeline(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`.
......@@ -355,7 +355,7 @@ class VersatileDiffusionPipeline(DiffusionPipeline):
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/deprecated/versatile_diffusion/pipeline_versatile_diffusion_dual_guided.py
View file @ be4afa0b
......@@ -395,10 +395,10 @@ class VersatileDiffusionDualGuidedPipeline(DiffusionPipeline):
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,
**kwargs,
):
......@@ -429,7 +429,7 @@ class VersatileDiffusionDualGuidedPipeline(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`.
......@@ -439,7 +439,7 @@ class VersatileDiffusionDualGuidedPipeline(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/deprecated/versatile_diffusion/pipeline_versatile_diffusion_image_variation.py
View file @ be4afa0b
......@@ -197,7 +197,7 @@ class VersatileDiffusionImageVariationPipeline(DiffusionPipeline):
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)}"
)
......@@ -247,10 +247,10 @@ class VersatileDiffusionImageVariationPipeline(DiffusionPipeline):
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,
**kwargs,
):
......@@ -281,7 +281,7 @@ class VersatileDiffusionImageVariationPipeline(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`.
......@@ -292,7 +292,7 @@ class VersatileDiffusionImageVariationPipeline(DiffusionPipeline):
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/deprecated/versatile_diffusion/pipeline_versatile_diffusion_text_to_image.py
View file @ be4afa0b
......@@ -333,10 +333,10 @@ class VersatileDiffusionTextToImagePipeline(DiffusionPipeline):
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,
**kwargs,
):
......@@ -367,7 +367,7 @@ class VersatileDiffusionTextToImagePipeline(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`.
......@@ -378,7 +378,7 @@ class VersatileDiffusionTextToImagePipeline(DiffusionPipeline):
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/deprecated/vq_diffusion/pipeline_vq_diffusion.py
View file @ be4afa0b
......@@ -169,10 +169,10 @@ class VQDiffusionPipeline(DiffusionPipeline):
truncation_rate: float = 1.0,
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: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
) -> Union[ImagePipelineOutput, Tuple]:
"""
......@@ -196,7 +196,7 @@ class VQDiffusionPipeline(DiffusionPipeline):
generator (`torch.Generator`, *optional*):
A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html) to make
generation deterministic.
latents (`torch.FloatTensor` of shape (batch), *optional*):
latents (`torch.Tensor` of shape (batch), *optional*):
Pre-generated noisy latents sampled from a Gaussian distribution, to be used as inputs for image
generation. Must be valid embedding indices.If not provided, a latents tensor will be generated of
completely masked latent pixels.
......@@ -206,7 +206,7 @@ class VQDiffusionPipeline(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.
......@@ -301,7 +301,7 @@ class VQDiffusionPipeline(DiffusionPipeline):
return ImagePipelineOutput(images=image)
def truncate(self, log_p_x_0: torch.FloatTensor, truncation_rate: float) -> torch.FloatTensor:
def truncate(self, log_p_x_0: torch.Tensor, truncation_rate: float) -> torch.Tensor:
"""
Truncates `log_p_x_0` such that for each column vector, the total cumulative probability is `truncation_rate`
The lowest probabilities that would increase the cumulative probability above `truncation_rate` are set to
......
src/diffusers/pipelines/i2vgen_xl/pipeline_i2vgen_xl.py
View file @ be4afa0b
......@@ -154,8 +154,8 @@ class I2VGenXLPipeline(
device,
num_videos_per_prompt,
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,
clip_skip: Optional[int] = None,
):
r"""
......@@ -174,10 +174,10 @@ class I2VGenXLPipeline(
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.
......@@ -434,7 +434,7 @@ class I2VGenXLPipeline(
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)}"
)
......@@ -513,9 +513,9 @@ class I2VGenXLPipeline(
num_videos_per_prompt: Optional[int] = 1,
decode_chunk_size: Optional[int] = 1,
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,
......@@ -527,7 +527,7 @@ class I2VGenXLPipeline(
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 (`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`):
......@@ -559,14 +559,14 @@ class I2VGenXLPipeline(
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/kandinsky/pipeline_kandinsky.py
View file @ be4afa0b
......@@ -233,8 +233,8 @@ class KandinskyPipeline(DiffusionPipeline):
def __call__(
self,
prompt: Union[str, List[str]],
image_embeds: Union[torch.FloatTensor, List[torch.FloatTensor]],
negative_image_embeds: Union[torch.FloatTensor, List[torch.FloatTensor]],
image_embeds: Union[torch.Tensor, List[torch.Tensor]],
negative_image_embeds: Union[torch.Tensor, List[torch.Tensor]],
negative_prompt: Optional[Union[str, List[str]]] = None,
height: int = 512,
width: int = 512,
......@@ -242,9 +242,9 @@ class KandinskyPipeline(DiffusionPipeline):
guidance_scale: float = 4.0,
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",
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
return_dict: bool = True,
):
......@@ -254,9 +254,9 @@ class KandinskyPipeline(DiffusionPipeline):
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
image_embeds (`torch.FloatTensor` or `List[torch.FloatTensor]`):
image_embeds (`torch.Tensor` or `List[torch.Tensor]`):
The clip image embeddings for text prompt, that will be used to condition the image generation.
negative_image_embeds (`torch.FloatTensor` or `List[torch.FloatTensor]`):
negative_image_embeds (`torch.Tensor` or `List[torch.Tensor]`):
The clip image embeddings for negative text prompt, will be used to condition the image generation.
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
......@@ -279,7 +279,7 @@ class KandinskyPipeline(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`.
......@@ -288,7 +288,7 @@ class KandinskyPipeline(DiffusionPipeline):
(`np.array`) or `"pt"` (`torch.Tensor`).
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/kandinsky/pipeline_kandinsky_combined.py
View file @ be4afa0b
......@@ -226,9 +226,9 @@ class KandinskyCombinedPipeline(DiffusionPipeline):
prior_guidance_scale: float = 4.0,
prior_num_inference_steps: int = 25,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
return_dict: bool = True,
):
......@@ -268,7 +268,7 @@ class KandinskyCombinedPipeline(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`.
......@@ -277,7 +277,7 @@ class KandinskyCombinedPipeline(DiffusionPipeline):
(`np.array`) or `"pt"` (`torch.Tensor`).
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.
......@@ -436,7 +436,7 @@ class KandinskyImg2ImgCombinedPipeline(DiffusionPipeline):
def __call__(
self,
prompt: Union[str, List[str]],
image: Union[torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]],
image: Union[torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]],
negative_prompt: Optional[Union[str, List[str]]] = None,
num_inference_steps: int = 100,
guidance_scale: float = 4.0,
......@@ -447,9 +447,9 @@ class KandinskyImg2ImgCombinedPipeline(DiffusionPipeline):
prior_guidance_scale: float = 4.0,
prior_num_inference_steps: int = 25,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
return_dict: bool = True,
):
......@@ -459,7 +459,7 @@ class KandinskyImg2ImgCombinedPipeline(DiffusionPipeline):
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
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, that will be used as the starting point for the
process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
again.
......@@ -499,7 +499,7 @@ class KandinskyImg2ImgCombinedPipeline(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`.
......@@ -508,7 +508,7 @@ class KandinskyImg2ImgCombinedPipeline(DiffusionPipeline):
(`np.array`) or `"pt"` (`torch.Tensor`).
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.
......@@ -677,8 +677,8 @@ class KandinskyInpaintCombinedPipeline(DiffusionPipeline):
def __call__(
self,
prompt: Union[str, List[str]],
image: Union[torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]],
mask_image: Union[torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]],
image: Union[torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]],
mask_image: Union[torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]],
negative_prompt: Optional[Union[str, List[str]]] = None,
num_inference_steps: int = 100,
guidance_scale: float = 4.0,
......@@ -688,9 +688,9 @@ class KandinskyInpaintCombinedPipeline(DiffusionPipeline):
prior_guidance_scale: float = 4.0,
prior_num_inference_steps: int = 25,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
latents: Optional[torch.FloatTensor] = None,
latents: Optional[torch.Tensor] = None,
output_type: Optional[str] = "pil",
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
return_dict: bool = True,
):
......@@ -700,7 +700,7 @@ class KandinskyInpaintCombinedPipeline(DiffusionPipeline):
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
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, that will be used as the starting point for the
process. Can also accept image latents as `image`, if passing latents directly, it will not be encoded
again.
......@@ -739,7 +739,7 @@ class KandinskyInpaintCombinedPipeline(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`.
......@@ -748,7 +748,7 @@ class KandinskyInpaintCombinedPipeline(DiffusionPipeline):
(`np.array`) or `"pt"` (`torch.Tensor`).
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/kandinsky/pipeline_kandinsky_img2img.py
View file @ be4afa0b
......@@ -266,10 +266,10 @@ class KandinskyImg2ImgPipeline(DiffusionPipeline):
# add_noise method to overwrite the one in schedule because it use a different beta schedule for adding noise vs sampling
def add_noise(
self,
original_samples: torch.FloatTensor,
noise: torch.FloatTensor,
original_samples: torch.Tensor,
noise: torch.Tensor,
timesteps: torch.IntTensor,
) -> torch.FloatTensor:
) -> torch.Tensor:
betas = torch.linspace(0.0001, 0.02, 1000, dtype=torch.float32)
alphas = 1.0 - betas
alphas_cumprod = torch.cumprod(alphas, dim=0)
......@@ -295,9 +295,9 @@ class KandinskyImg2ImgPipeline(DiffusionPipeline):
def __call__(
self,
prompt: Union[str, List[str]],
image: Union[torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]],
image_embeds: torch.FloatTensor,
negative_image_embeds: torch.FloatTensor,
image: Union[torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]],
image_embeds: torch.Tensor,
negative_image_embeds: torch.Tensor,
negative_prompt: Optional[Union[str, List[str]]] = None,
height: int = 512,
width: int = 512,
......@@ -307,7 +307,7 @@ class KandinskyImg2ImgPipeline(DiffusionPipeline):
num_images_per_prompt: int = 1,
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
output_type: Optional[str] = "pil",
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
return_dict: bool = True,
):
......@@ -317,12 +317,12 @@ class KandinskyImg2ImgPipeline(DiffusionPipeline):
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
image (`torch.FloatTensor`, `PIL.Image.Image`):
image (`torch.Tensor`, `PIL.Image.Image`):
`Image`, or tensor representing an image batch, that will be used as the starting point for the
process.
image_embeds (`torch.FloatTensor` or `List[torch.FloatTensor]`):
image_embeds (`torch.Tensor` or `List[torch.Tensor]`):
The clip image embeddings for text prompt, that will be used to condition the image generation.
negative_image_embeds (`torch.FloatTensor` or `List[torch.FloatTensor]`):
negative_image_embeds (`torch.Tensor` or `List[torch.Tensor]`):
The clip image embeddings for negative text prompt, will be used to condition the image generation.
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
......@@ -356,7 +356,7 @@ class KandinskyImg2ImgPipeline(DiffusionPipeline):
(`np.array`) or `"pt"` (`torch.Tensor`).
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/kandinsky/pipeline_kandinsky_inpaint.py
View file @ be4afa0b
......@@ -398,10 +398,10 @@ class KandinskyInpaintPipeline(DiffusionPipeline):
def __call__(
self,
prompt: Union[str, List[str]],
image: Union[torch.FloatTensor, PIL.Image.Image],
mask_image: Union[torch.FloatTensor, PIL.Image.Image, np.ndarray],
image_embeds: torch.FloatTensor,
negative_image_embeds: torch.FloatTensor,
image: Union[torch.Tensor, PIL.Image.Image],
mask_image: Union[torch.Tensor, PIL.Image.Image, np.ndarray],
image_embeds: torch.Tensor,
negative_image_embeds: torch.Tensor,
negative_prompt: Optional[Union[str, List[str]]] = None,
height: int = 512,
width: int = 512,
......@@ -409,9 +409,9 @@ class KandinskyInpaintPipeline(DiffusionPipeline):
guidance_scale: float = 4.0,
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",
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
callback: Optional[Callable[[int, int, torch.Tensor], None]] = None,
callback_steps: int = 1,
return_dict: bool = True,
):
......@@ -421,10 +421,10 @@ class KandinskyInpaintPipeline(DiffusionPipeline):
Args:
prompt (`str` or `List[str]`):
The prompt or prompts to guide the image generation.
image (`torch.FloatTensor`, `PIL.Image.Image` or `np.ndarray`):
image (`torch.Tensor`, `PIL.Image.Image` or `np.ndarray`):
`Image`, or tensor representing an image batch, that will be used as the starting point for the
process.
mask_image (`PIL.Image.Image`,`torch.FloatTensor` or `np.ndarray`):
mask_image (`PIL.Image.Image`,`torch.Tensor` or `np.ndarray`):
`Image`, or a tensor representing an image batch, to mask `image`. White pixels in the mask will be
repainted, while black pixels will be preserved. You can pass a pytorch tensor as mask only if the
image you passed is a pytorch tensor, and it should contain one color channel (L) instead of 3, so the
......@@ -432,9 +432,9 @@ class KandinskyInpaintPipeline(DiffusionPipeline):
image or numpy array, mask should also be a either PIL image or numpy array. If it is a PIL image, it
will be converted to a single channel (luminance) before use. If it is a nummpy array, the expected
shape is `(H, W)`.
image_embeds (`torch.FloatTensor` or `List[torch.FloatTensor]`):
image_embeds (`torch.Tensor` or `List[torch.Tensor]`):
The clip image embeddings for text prompt, that will be used to condition the image generation.
negative_image_embeds (`torch.FloatTensor` or `List[torch.FloatTensor]`):
negative_image_embeds (`torch.Tensor` or `List[torch.Tensor]`):
The clip image embeddings for negative text prompt, will be used to condition the image generation.
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
......@@ -457,7 +457,7 @@ class KandinskyInpaintPipeline(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`.
......@@ -466,7 +466,7 @@ class KandinskyInpaintPipeline(DiffusionPipeline):
(`np.array`) or `"pt"` (`torch.Tensor`).
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/kandinsky/pipeline_kandinsky_prior.py
View file @ be4afa0b
......@@ -115,14 +115,14 @@ class KandinskyPriorPipelineOutput(BaseOutput):
Output class for KandinskyPriorPipeline.
Args:
image_embeds (`torch.FloatTensor`)
image_embeds (`torch.Tensor`)
clip image embeddings for text prompt
negative_image_embeds (`List[PIL.Image.Image]` or `np.ndarray`)
clip image embeddings for unconditional tokens
"""
image_embeds: Union[torch.FloatTensor, np.ndarray]
negative_image_embeds: Union[torch.FloatTensor, np.ndarray]
image_embeds: Union[torch.Tensor, np.ndarray]
negative_image_embeds: Union[torch.Tensor, np.ndarray]
class KandinskyPriorPipeline(DiffusionPipeline):
......@@ -173,12 +173,12 @@ class KandinskyPriorPipeline(DiffusionPipeline):
@replace_example_docstring(EXAMPLE_INTERPOLATE_DOC_STRING)
def interpolate(
self,
images_and_prompts: List[Union[str, PIL.Image.Image, torch.FloatTensor]],
images_and_prompts: List[Union[str, PIL.Image.Image, torch.Tensor]],
weights: List[float],
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,
negative_prior_prompt: Optional[str] = None,
negative_prompt: str = "",
guidance_scale: float = 4.0,
......@@ -188,7 +188,7 @@ class KandinskyPriorPipeline(DiffusionPipeline):
Function invoked when using the prior pipeline for interpolation.
Args:
images_and_prompts (`List[Union[str, PIL.Image.Image, torch.FloatTensor]]`):
images_and_prompts (`List[Union[str, PIL.Image.Image, torch.Tensor]]`):
list of prompts and images to guide the image generation.
weights: (`List[float]`):
list of weights for each condition in `images_and_prompts`
......@@ -200,7 +200,7 @@ class KandinskyPriorPipeline(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`.
......@@ -403,7 +403,7 @@ class KandinskyPriorPipeline(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,
output_type: Optional[str] = "pt",
return_dict: bool = True,
......@@ -425,7 +425,7 @@ class KandinskyPriorPipeline(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`.
......
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