diffusers 0.27.0__py3-none-any.whl → 0.32.2__py3-none-any.whl

diffusers/pipelines/kandinsky2_2/pipeline_kandinsky2_2_prior_emb2emb.py

@@ -108,7 +108,7 @@ class KandinskyV22PriorEmb2EmbPipeline(DiffusionPipeline):
 
     Args:
         prior ([`PriorTransformer`]):
-            The canonincal unCLIP prior to approximate the image embedding from the text embedding.
+            The canonical unCLIP prior to approximate the image embedding from the text embedding.
         image_encoder ([`CLIPVisionModelWithProjection`]):
             Frozen image-encoder.
         text_encoder ([`CLIPTextModelWithProjection`]):
@@ -156,12 +156,12 @@ class KandinskyV22PriorEmb2EmbPipeline(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,
@@ -171,7 +171,7 @@ class KandinskyV22PriorEmb2EmbPipeline(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`
@@ -183,7 +183,7 @@ class KandinskyV22PriorEmb2EmbPipeline(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`.
@@ -418,7 +418,7 @@ class KandinskyV22PriorEmb2EmbPipeline(DiffusionPipeline):
                 Conceptually, indicates how much to transform the reference `emb`. Must be between 0 and 1. `image`
                 will be used as a starting point, adding more noise to it the larger the `strength`. The number of
                 denoising steps depends on the amount of noise initially added.
-            emb (`torch.FloatTensor`):
+            emb (`torch.Tensor`):
                 The image embedding.
             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

diffusers/pipelines/kandinsky3/convert_kandinsky3_unet.py

@@ -35,10 +35,10 @@ DYNAMIC_MAP = {
 
 def convert_state_dict(unet_state_dict):
     """
-    Convert the state dict of a U-Net model to match the key format expected by Kandinsky3UNet model.
     Args:
-        unet_model (torch.nn.Module): The original U-Net model.
-        unet_kandi3_model (torch.nn.Module): The Kandinsky3UNet model to match keys with.
+    Convert the state dict of a U-Net model to match the key format expected by Kandinsky3UNet model.
+        unet_model (torch.nn.Module): The original U-Net model. unet_kandi3_model (torch.nn.Module): The Kandinsky3UNet
+        model to match keys with.
 
     Returns:
         OrderedDict: The converted state dictionary.

diffusers/pipelines/kandinsky3/pipeline_kandinsky3.py

@@ -3,12 +3,11 @@ from typing import Callable, Dict, List, Optional, Union
 import torch
 from transformers import T5EncoderModel, T5Tokenizer
 
-from ...loaders import LoraLoaderMixin
+from ...loaders import StableDiffusionLoraLoaderMixin
 from ...models import Kandinsky3UNet, VQModel
 from ...schedulers import DDPMScheduler
 from ...utils import (
     deprecate,
-    is_accelerate_available,
     logging,
     replace_example_docstring,
 )
@@ -24,7 +23,9 @@ EXAMPLE_DOC_STRING = """
         >>> from diffusers import AutoPipelineForText2Image
         >>> import torch
 
-        >>> pipe = AutoPipelineForText2Image.from_pretrained("kandinsky-community/kandinsky-3", variant="fp16", torch_dtype=torch.float16)
+        >>> pipe = AutoPipelineForText2Image.from_pretrained(
+        ...     "kandinsky-community/kandinsky-3", variant="fp16", torch_dtype=torch.float16
+        ... )
         >>> pipe.enable_model_cpu_offload()
 
         >>> prompt = "A photograph of the inside of a subway train. There are raccoons sitting on the seats. One of them is reading a newspaper. The window shows the city in the background."
@@ -46,7 +47,7 @@ def downscale_height_and_width(height, width, scale_factor=8):
     return new_height * scale_factor, new_width * scale_factor
 
 
-class Kandinsky3Pipeline(DiffusionPipeline, LoraLoaderMixin):
+class Kandinsky3Pipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixin):
     model_cpu_offload_seq = "text_encoder->unet->movq"
     _callback_tensor_inputs = [
         "latents",
@@ -70,20 +71,6 @@ class Kandinsky3Pipeline(DiffusionPipeline, LoraLoaderMixin):
             tokenizer=tokenizer, text_encoder=text_encoder, unet=unet, scheduler=scheduler, movq=movq
         )
 
-    def remove_all_hooks(self):
-        if is_accelerate_available():
-            from accelerate.hooks import remove_hook_from_module
-        else:
-            raise ImportError("Please install accelerate via `pip install accelerate`")
-
-        for model in [self.text_encoder, self.unet, self.movq]:
-            if model is not None:
-                remove_hook_from_module(model, recurse=True)
-
-        self.unet_offload_hook = None
-        self.text_encoder_offload_hook = None
-        self.final_offload_hook = None
-
     def process_embeds(self, embeddings, attention_mask, cut_context):
         if cut_context:
             embeddings[attention_mask == 0] = torch.zeros_like(embeddings[attention_mask == 0])
@@ -100,11 +87,11 @@ class Kandinsky3Pipeline(DiffusionPipeline, LoraLoaderMixin):
         num_images_per_prompt=1,
         device=None,
         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,
         _cut_context=False,
-        attention_mask: Optional[torch.FloatTensor] = None,
-        negative_attention_mask: Optional[torch.FloatTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        negative_attention_mask: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -122,16 +109,16 @@ class Kandinsky3Pipeline(DiffusionPipeline, LoraLoaderMixin):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
-            attention_mask (`torch.FloatTensor`, *optional*):
+            attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated attention mask. Must provide if passing `prompt_embeds` directly.
-            negative_attention_mask (`torch.FloatTensor`, *optional*):
+            negative_attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated negative attention mask. Must provide if passing `negative_prompt_embeds` directly.
         """
         if prompt is not None and negative_prompt is not None:
@@ -347,10 +334,10 @@ class Kandinsky3Pipeline(DiffusionPipeline, LoraLoaderMixin):
         height: Optional[int] = 1024,
         width: Optional[int] = 1024,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        attention_mask: Optional[torch.FloatTensor] = None,
-        negative_attention_mask: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        negative_attention_mask: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         latents=None,
@@ -393,16 +380,16 @@ class Kandinsky3Pipeline(DiffusionPipeline, LoraLoaderMixin):
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
-            attention_mask (`torch.FloatTensor`, *optional*):
+            attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated attention mask. Must provide if passing `prompt_embeds` directly.
-            negative_attention_mask (`torch.FloatTensor`, *optional*):
+            negative_attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated negative attention mask. Must provide if passing `negative_prompt_embeds` directly.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between
@@ -411,7 +398,7 @@ class Kandinsky3Pipeline(DiffusionPipeline, LoraLoaderMixin):
                 Whether or not to return a [`~pipelines.stable_diffusion.IFPipelineOutput`] instead of a plain tuple.
             callback (`Callable`, *optional*):
                 A function that will be called every `callback_steps` steps during inference. The function will be
-                called with the following arguments: `callback(step: int, timestep: int, latents: torch.FloatTensor)`.
+                called with the following arguments: `callback(step: int, timestep: int, latents: torch.Tensor)`.
             callback_steps (`int`, *optional*, defaults to 1):
                 The frequency at which the `callback` function will be called. If not specified, the callback will be
                 called at every step.

diffusers/pipelines/kandinsky3/pipeline_kandinsky3_img2img.py

@@ -7,12 +7,11 @@ import PIL.Image
 import torch
 from transformers import T5EncoderModel, T5Tokenizer
 
-from ...loaders import LoraLoaderMixin
+from ...loaders import StableDiffusionLoraLoaderMixin
 from ...models import Kandinsky3UNet, VQModel
 from ...schedulers import DDPMScheduler
 from ...utils import (
     deprecate,
-    is_accelerate_available,
     logging,
     replace_example_docstring,
 )
@@ -29,11 +28,15 @@ EXAMPLE_DOC_STRING = """
         >>> from diffusers.utils import load_image
         >>> import torch
 
-        >>> pipe = AutoPipelineForImage2Image.from_pretrained("kandinsky-community/kandinsky-3", variant="fp16", torch_dtype=torch.float16)
+        >>> pipe = AutoPipelineForImage2Image.from_pretrained(
+        ...     "kandinsky-community/kandinsky-3", variant="fp16", torch_dtype=torch.float16
+        ... )
         >>> pipe.enable_model_cpu_offload()
 
         >>> prompt = "A painting of the inside of a subway train with tiny raccoons."
-        >>> image = load_image("https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky3/t2i.png")
+        >>> image = load_image(
+        ...     "https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinsky3/t2i.png"
+        ... )
 
         >>> generator = torch.Generator(device="cpu").manual_seed(0)
         >>> image = pipe(prompt, image=image, strength=0.75, num_inference_steps=25, generator=generator).images[0]
@@ -59,7 +62,7 @@ def prepare_image(pil_image):
     return image
 
 
-class Kandinsky3Img2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
+class Kandinsky3Img2ImgPipeline(DiffusionPipeline, StableDiffusionLoraLoaderMixin):
     model_cpu_offload_seq = "text_encoder->movq->unet->movq"
     _callback_tensor_inputs = [
         "latents",
@@ -92,20 +95,6 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
 
         return timesteps, num_inference_steps - t_start
 
-    def remove_all_hooks(self):
-        if is_accelerate_available():
-            from accelerate.hooks import remove_hook_from_module
-        else:
-            raise ImportError("Please install accelerate via `pip install accelerate`")
-
-        for model in [self.text_encoder, self.unet]:
-            if model is not None:
-                remove_hook_from_module(model, recurse=True)
-
-        self.unet_offload_hook = None
-        self.text_encoder_offload_hook = None
-        self.final_offload_hook = None
-
     def _process_embeds(self, embeddings, attention_mask, cut_context):
         # return embeddings, attention_mask
         if cut_context:
@@ -123,11 +112,11 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
         num_images_per_prompt=1,
         device=None,
         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,
         _cut_context=False,
-        attention_mask: Optional[torch.FloatTensor] = None,
-        negative_attention_mask: Optional[torch.FloatTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        negative_attention_mask: Optional[torch.Tensor] = None,
     ):
         r"""
         Encodes the prompt into text encoder hidden states.
@@ -145,16 +134,16 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
                 The prompt or prompts not to guide the image generation. If not defined, one has to pass
                 `negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
                 Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
-            attention_mask (`torch.FloatTensor`, *optional*):
+            attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated attention mask. Must provide if passing `prompt_embeds` directly.
-            negative_attention_mask (`torch.FloatTensor`, *optional*):
+            negative_attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated negative attention mask. Must provide if passing `negative_prompt_embeds` directly.
         """
         if prompt is not None and negative_prompt is not None:
@@ -414,17 +403,17 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
     def __call__(
         self,
         prompt: Union[str, List[str]] = None,
-        image: Union[torch.FloatTensor, PIL.Image.Image, List[torch.FloatTensor], List[PIL.Image.Image]] = None,
+        image: Union[torch.Tensor, PIL.Image.Image, List[torch.Tensor], List[PIL.Image.Image]] = None,
         strength: float = 0.3,
         num_inference_steps: int = 25,
         guidance_scale: float = 3.0,
         negative_prompt: Optional[Union[str, List[str]]] = None,
         num_images_per_prompt: Optional[int] = 1,
         generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
-        prompt_embeds: Optional[torch.FloatTensor] = None,
-        negative_prompt_embeds: Optional[torch.FloatTensor] = None,
-        attention_mask: Optional[torch.FloatTensor] = None,
-        negative_attention_mask: Optional[torch.FloatTensor] = None,
+        prompt_embeds: Optional[torch.Tensor] = None,
+        negative_prompt_embeds: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        negative_attention_mask: Optional[torch.Tensor] = None,
         output_type: Optional[str] = "pil",
         return_dict: bool = True,
         callback_on_step_end: Optional[Callable[[int, int, Dict], None]] = None,
@@ -438,7 +427,7 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
             prompt (`str` or `List[str]`, *optional*):
                 The prompt or prompts to guide the image generation. If not defined, one has to pass `prompt_embeds`.
                 instead.
-            image (`torch.FloatTensor`, `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.
             strength (`float`, *optional*, defaults to 0.8):
@@ -465,16 +454,16 @@ class Kandinsky3Img2ImgPipeline(DiffusionPipeline, LoraLoaderMixin):
             generator (`torch.Generator` or `List[torch.Generator]`, *optional*):
                 One or a list of [torch generator(s)](https://pytorch.org/docs/stable/generated/torch.Generator.html)
                 to make generation deterministic.
-            prompt_embeds (`torch.FloatTensor`, *optional*):
+            prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
                 provided, text embeddings will be generated from `prompt` input argument.
-            negative_prompt_embeds (`torch.FloatTensor`, *optional*):
+            negative_prompt_embeds (`torch.Tensor`, *optional*):
                 Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
                 weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
                 argument.
-            attention_mask (`torch.FloatTensor`, *optional*):
+            attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated attention mask. Must provide if passing `prompt_embeds` directly.
-            negative_attention_mask (`torch.FloatTensor`, *optional*):
+            negative_attention_mask (`torch.Tensor`, *optional*):
                 Pre-generated negative attention mask. Must provide if passing `negative_prompt_embeds` directly.
             output_type (`str`, *optional*, defaults to `"pil"`):
                 The output format of the generate image. Choose between

diffusers/pipelines/kolors/__init__.py

@@ -0,0 +1,54 @@
+from typing import TYPE_CHECKING
+
+from ...utils import (
+    DIFFUSERS_SLOW_IMPORT,
+    OptionalDependencyNotAvailable,
+    _LazyModule,
+    get_objects_from_module,
+    is_sentencepiece_available,
+    is_torch_available,
+    is_transformers_available,
+)
+
+
+_dummy_objects = {}
+_import_structure = {}
+
+try:
+    if not (is_transformers_available() and is_torch_available()) and is_sentencepiece_available():
+        raise OptionalDependencyNotAvailable()
+except OptionalDependencyNotAvailable:
+    from ...utils import dummy_torch_and_transformers_and_sentencepiece_objects  # noqa F403
+
+    _dummy_objects.update(get_objects_from_module(dummy_torch_and_transformers_and_sentencepiece_objects))
+else:
+    _import_structure["pipeline_kolors"] = ["KolorsPipeline"]
+    _import_structure["pipeline_kolors_img2img"] = ["KolorsImg2ImgPipeline"]
+    _import_structure["text_encoder"] = ["ChatGLMModel"]
+    _import_structure["tokenizer"] = ["ChatGLMTokenizer"]
+
+if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
+    try:
+        if not (is_transformers_available() and is_torch_available()) and is_sentencepiece_available():
+            raise OptionalDependencyNotAvailable()
+    except OptionalDependencyNotAvailable:
+        from ...utils.dummy_torch_and_transformers_and_sentencepiece_objects import *
+
+    else:
+        from .pipeline_kolors import KolorsPipeline
+        from .pipeline_kolors_img2img import KolorsImg2ImgPipeline
+        from .text_encoder import ChatGLMModel
+        from .tokenizer import ChatGLMTokenizer
+
+else:
+    import sys
+
+    sys.modules[__name__] = _LazyModule(
+        __name__,
+        globals()["__file__"],
+        _import_structure,
+        module_spec=__spec__,
+    )
+
+    for name, value in _dummy_objects.items():
+        setattr(sys.modules[__name__], name, value)