v1-5 docs updates (huggingface#921)

* Update README.md

Additionally add FLAX so the model card can be slimmer and point to this page

* Find and replace all

* v-1-5 -> v1-5

* revert test changes

* Update README.md

Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>

* Update docs/source/quicktour.mdx

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update README.md

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update docs/source/quicktour.mdx

Co-authored-by: Pedro Cuenca <pedro@huggingface.co>

* Update README.md

Co-authored-by: Suraj Patil <surajp815@gmail.com>

* Revert certain references to v1-5

* Docs changes

* Apply suggestions from code review

Co-authored-by: apolinario <joaopaulo.passos+multimodal@gmail.com>
Co-authored-by: anton-l <anton@huggingface.co>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Pedro Cuenca <pedro@huggingface.co>
Co-authored-by: Suraj Patil <surajp815@gmail.com>

modeling_flax_utils.py

@@ -105,14 +105,14 @@ def to_bf16(self, params: Union[Dict, FrozenDict], mask: Any = None):
         >>> from diffusers import FlaxUNet2DConditionModel
 
         >>> # load model
-        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> # By default, the model parameters will be in fp32 precision, to cast these to bfloat16 precision
         >>> params = model.to_bf16(params)
         >>> # If you don't want to cast certain parameters (for example layer norm bias and scale)
         >>> # then pass the mask as follows
         >>> from flax import traverse_util
 
-        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> flat_params = traverse_util.flatten_dict(params)
         >>> mask = {
         ...     path: (path[-2] != ("LayerNorm", "bias") and path[-2:] != ("LayerNorm", "scale"))
@@ -141,7 +141,7 @@ def to_fp32(self, params: Union[Dict, FrozenDict], mask: Any = None):
         >>> from diffusers import FlaxUNet2DConditionModel
 
         >>> # Download model and configuration from huggingface.co
-        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> # By default, the model params will be in fp32, to illustrate the use of this method,
         >>> # we'll first cast to fp16 and back to fp32
         >>> params = model.to_f16(params)
@@ -171,14 +171,14 @@ def to_fp16(self, params: Union[Dict, FrozenDict], mask: Any = None):
         >>> from diffusers import FlaxUNet2DConditionModel
 
         >>> # load model
-        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> # By default, the model params will be in fp32, to cast these to float16
         >>> params = model.to_fp16(params)
         >>> # If you want don't want to cast certain parameters (for example layer norm bias and scale)
         >>> # then pass the mask as follows
         >>> from flax import traverse_util
 
-        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> flat_params = traverse_util.flatten_dict(params)
         >>> mask = {
         ...     path: (path[-2] != ("LayerNorm", "bias") and path[-2:] != ("LayerNorm", "scale"))
@@ -216,7 +216,7 @@ def from_pretrained(
 
                     - A string, the *model id* of a pretrained model hosted inside a model repo on huggingface.co.
                       Valid model ids are namespaced under a user or organization name, like
-                      `CompVis/stable-diffusion-v1-4`.
+                      `runwayml/stable-diffusion-v1-5`.
                     - A path to a *directory* containing model weights saved using [`~ModelMixin.save_pretrained`],
                       e.g., `./my_model_directory/`.
             dtype (`jax.numpy.dtype`, *optional*, defaults to `jax.numpy.float32`):
@@ -273,7 +273,7 @@ def from_pretrained(
         >>> from diffusers import FlaxUNet2DConditionModel
 
         >>> # Download model and configuration from huggingface.co and cache.
-        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> model, params = FlaxUNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5")
         >>> # Model was saved using *save_pretrained('./test/saved_model/')* (for example purposes, not runnable).
         >>> model, params = FlaxUNet2DConditionModel.from_pretrained("./test/saved_model/")
         ```"""

pipeline_flax_utils.py

@@ -244,7 +244,7 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
         <Tip>
 
          It is required to be logged in (`huggingface-cli login`) when you want to use private or [gated
-         models](https://huggingface.co/docs/hub/models-gated#gated-models), *e.g.* `"CompVis/stable-diffusion-v1-4"`
+         models](https://huggingface.co/docs/hub/models-gated#gated-models), *e.g.* `"runwayml/stable-diffusion-v1-5"`
 
         </Tip>
 
@@ -266,13 +266,13 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
         >>> # Download pipeline that requires an authorization token
         >>> # For more information on access tokens, please refer to this section
         >>> # of the documentation](https://huggingface.co/docs/hub/security-tokens)
-        >>> pipeline = FlaxDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> pipeline = FlaxDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
 
         >>> # Download pipeline, but overwrite scheduler
         >>> from diffusers import LMSDiscreteScheduler
 
         >>> scheduler = LMSDiscreteScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear")
-        >>> pipeline = FlaxDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", scheduler=scheduler)
+        >>> pipeline = FlaxDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", scheduler=scheduler)
         ```
         """
         cache_dir = kwargs.pop("cache_dir", DIFFUSERS_CACHE)

pipeline_utils.py

@@ -317,7 +317,7 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
         <Tip>
 
          It is required to be logged in (`huggingface-cli login`) when you want to use private or [gated
-         models](https://huggingface.co/docs/hub/models-gated#gated-models), *e.g.* `"CompVis/stable-diffusion-v1-4"`
+         models](https://huggingface.co/docs/hub/models-gated#gated-models), *e.g.* `"runwayml/stable-diffusion-v1-5"`
 
         </Tip>
 
@@ -339,13 +339,13 @@ def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.P
         >>> # Download pipeline that requires an authorization token
         >>> # For more information on access tokens, please refer to this section
         >>> # of the documentation](https://huggingface.co/docs/hub/security-tokens)
-        >>> pipeline = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
+        >>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
 
         >>> # Download pipeline, but overwrite scheduler
         >>> from diffusers import LMSDiscreteScheduler
 
         >>> scheduler = LMSDiscreteScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear")
-        >>> pipeline = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", scheduler=scheduler)
+        >>> pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", scheduler=scheduler)
         ```
         """
         cache_dir = kwargs.pop("cache_dir", DIFFUSERS_CACHE)

pipelines/README.md

@@ -55,8 +55,8 @@ Diffusion models often consist of multiple independently-trained models or other
 Each model has been trained independently on a different task and the scheduler can easily be swapped out and replaced with a different one. 
 During inference, we however want to be able to easily load all components and use them in inference - even if one component, *e.g.* CLIP's text encoder, originates from a different library, such as [Transformers](https://github.com/huggingface/transformers). To that end, all pipelines provide the following functionality:
 
-- [`from_pretrained` method](https://github.com/huggingface/diffusers/blob/5cbed8e0d157f65d3ddc2420dfd09f2df630e978/src/diffusers/pipeline_utils.py#L139) that accepts a Hugging Face Hub repository id, *e.g.* [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-diffusion-v1-4) or a path to a local directory, *e.g.*
-"./stable-diffusion". To correctly retrieve which models and components should be loaded, one has to provide a `model_index.json` file, *e.g.* [CompVis/stable-diffusion-v1-4/model_index.json](https://huggingface.co/CompVis/stable-diffusion-v1-4/blob/main/model_index.json), which defines all components that should be 
+- [`from_pretrained` method](https://github.com/huggingface/diffusers/blob/5cbed8e0d157f65d3ddc2420dfd09f2df630e978/src/diffusers/pipeline_utils.py#L139) that accepts a Hugging Face Hub repository id, *e.g.* [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) or a path to a local directory, *e.g.*
+"./stable-diffusion". To correctly retrieve which models and components should be loaded, one has to provide a `model_index.json` file, *e.g.* [runwayml/stable-diffusion-v1-5/model_index.json](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/model_index.json), which defines all components that should be 
 loaded into the pipelines. More specifically, for each model/component one needs to define the format `<name>: ["<library>", "<class name>"]`. `<name>` is the attribute name given to the loaded instance of `<class name>` which can be found in the library or pipeline folder called `"<library>"`.
 - [`save_pretrained`](https://github.com/huggingface/diffusers/blob/5cbed8e0d157f65d3ddc2420dfd09f2df630e978/src/diffusers/pipeline_utils.py#L90) that accepts a local path, *e.g.* `./stable-diffusion` under which all models/components of the pipeline will be saved. For each component/model a folder is created inside the local path that is named after the given attribute name, *e.g.* `./stable_diffusion/unet`. 
 In addition, a `model_index.json` file is created at the root of the local path, *e.g.* `./stable_diffusion/model_index.json` so that the complete pipeline can again be instantiated 
@@ -88,7 +88,7 @@ logic including pre-processing, an unrolled diffusion loop, and post-processing
 # make sure you're logged in with `huggingface-cli login`
 from diffusers import StableDiffusionPipeline, LMSDiscreteScheduler
 
-pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
+pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
 pipe = pipe.to("cuda")
 
 prompt = "a photo of an astronaut riding a horse on mars"
@@ -111,7 +111,7 @@ from diffusers import StableDiffusionImg2ImgPipeline
 # load the pipeline
 device = "cuda"
 pipe = StableDiffusionImg2ImgPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4",
+    "runwayml/stable-diffusion-v1-5",
     revision="fp16", 
     torch_dtype=torch.float16,
 ).to(device)

pipelines/stable_diffusion/README.md

@@ -13,7 +13,7 @@ The summary of the model is the following:
 - Stable Diffusion has the same architecture as [Latent Diffusion](https://arxiv.org/abs/2112.10752) but uses a frozen CLIP Text Encoder instead of training the text encoder jointly with the diffusion model.
 - An in-detail explanation of the Stable Diffusion model can be found under [Stable Diffusion with 🧨 Diffusers](https://huggingface.co/blog/stable_diffusion).
 - If you don't want to rely on the Hugging Face Hub and having to pass a authentication token, you can 
-download the weights with `git lfs install; git clone https://huggingface.co/CompVis/stable-diffusion-v1-4` and instead pass the local path to the cloned folder to `from_pretrained` as shown below.
+download the weights with `git lfs install; git clone https://huggingface.co/runwayml/stable-diffusion-v1-5` and instead pass the local path to the cloned folder to `from_pretrained` as shown below.
 - Stable Diffusion can work with a variety of different samplers as is shown below.
 
 ## Available Pipelines:
@@ -33,22 +33,22 @@ If you want to download the model weights using a single Python line, you need t
 ```python
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
+pipeline = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
 ```
 
-This however can make it difficult to build applications on top of `diffusers` as you will always have to pass the token around. A potential way to solve this issue is by downloading the weights to a local path `"./stable-diffusion-v1-4"`:
+This however can make it difficult to build applications on top of `diffusers` as you will always have to pass the token around. A potential way to solve this issue is by downloading the weights to a local path `"./stable-diffusion-v1-5"`:
 
 ```
 git lfs install
-git clone https://huggingface.co/CompVis/stable-diffusion-v1-4
+git clone https://huggingface.co/runwayml/stable-diffusion-v1-5
 ```
 
 and simply passing the local path to `from_pretrained`:
 
 ```python
 from diffusers import StableDiffusionPipeline
 
-pipe = StableDiffusionPipeline.from_pretrained("./stable-diffusion-v1-4")
+pipe = StableDiffusionPipeline.from_pretrained("./stable-diffusion-v1-5")
 ```
 
 ### Text-to-Image with default PLMS scheduler
@@ -57,7 +57,7 @@ pipe = StableDiffusionPipeline.from_pretrained("./stable-diffusion-v1-4")
 # make sure you're logged in with `huggingface-cli login`
 from diffusers import StableDiffusionPipeline
 
-pipe = StableDiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4")
+pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5")
 pipe = pipe.to("cuda")
 
 prompt = "a photo of an astronaut riding a horse on mars"
@@ -75,7 +75,7 @@ from diffusers import StableDiffusionPipeline, DDIMScheduler
 scheduler = DDIMScheduler(beta_start=0.00085, beta_end=0.012, beta_schedule="scaled_linear", clip_sample=False, set_alpha_to_one=False)
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4", 
+    "runwayml/stable-diffusion-v1-5", 
     scheduler=scheduler,
 ).to("cuda")
 
@@ -98,7 +98,7 @@ lms = LMSDiscreteScheduler(
 )
 
 pipe = StableDiffusionPipeline.from_pretrained(
-    "CompVis/stable-diffusion-v1-4", 
+    "runwayml/stable-diffusion-v1-5", 
     scheduler=lms,
 ).to("cuda")
 

pipelines/stable_diffusion/pipeline_flax_stable_diffusion.py

@@ -45,7 +45,7 @@ class FlaxStableDiffusionPipeline(FlaxDiffusionPipeline):
             [`FlaxDDIMScheduler`], [`FlaxLMSDiscreteScheduler`], or [`FlaxPNDMScheduler`].
         safety_checker ([`FlaxStableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPFeatureExtractor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_img2img.py

@@ -50,7 +50,7 @@ class OnnxStableDiffusionImg2ImgPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPFeatureExtractor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

pipelines/stable_diffusion/pipeline_onnx_stable_diffusion_inpaint.py

@@ -63,7 +63,7 @@ class OnnxStableDiffusionInpaintPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPFeatureExtractor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

pipelines/stable_diffusion/pipeline_stable_diffusion.py

@@ -40,7 +40,7 @@ class StableDiffusionPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPFeatureExtractor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py

@@ -52,7 +52,7 @@ class StableDiffusionImg2ImgPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPFeatureExtractor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint.py

@@ -59,7 +59,7 @@ class StableDiffusionInpaintPipeline(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPFeatureExtractor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """

pipelines/stable_diffusion/pipeline_stable_diffusion_inpaint_legacy.py

@@ -66,7 +66,7 @@ class StableDiffusionInpaintPipelineLegacy(DiffusionPipeline):
             [`DDIMScheduler`], [`LMSDiscreteScheduler`], or [`PNDMScheduler`].
         safety_checker ([`StableDiffusionSafetyChecker`]):
             Classification module that estimates whether generated images could be considered offensive or harmful.
-            Please, refer to the [model card](https://huggingface.co/CompVis/stable-diffusion-v1-4) for details.
+            Please, refer to the [model card](https://huggingface.co/runwayml/stable-diffusion-v1-5) for details.
         feature_extractor ([`CLIPFeatureExtractor`]):
             Model that extracts features from generated images to be used as inputs for the `safety_checker`.
     """