StableDiffusionImageVariationPipeline (#1365)

* add StableDiffusionImageVariationPipeline * add ini init * use CLIPVisionModelWithProjection * fix _encode_image * add copied from * fix copies * add doc * handle tensor in _encode_image * add tests * correct model_id * remove copied from in enable_sequential_cpu_offload * fix tests * make slow tests pass * update slow tests * use temp model for now * fix test_stable_diffusion_img_variation_intermediate_state * fix test_stable_diffusion_img_variation_intermediate_state * check for torch.Tensor * quality * fix name * fix slow tests * install transformers from source * fix install * fix install * Apply suggestions from code review Co-authored-by: Pedro Cuenca <[email protected]> * input_image -> image * remove deprication warnings * fix test_stable_diffusion_img_variation_multiple_images * make flake happy Co-authored-by: Pedro Cuenca <[email protected]>
huggingface · Nov 23, 2022 · 0eb507f · 0eb507f
1 parent 9e234d8
commit 0eb507f
Show file tree

Hide file tree

Showing 9 changed files with 890 additions and 0 deletions.
diff --git a/.github/workflows/pr_tests.yml b/.github/workflows/pr_tests.yml
@@ -60,6 +60,7 @@ jobs:
       run: |
         python -m pip install -e .[quality,test]
         python -m pip install git+https://github.com/huggingface/accelerate
+        python -m pip install -U git+https://github.com/huggingface/transformers
 
     - name: Environment
       run: |
@@ -127,6 +128,7 @@ jobs:
         ${CONDA_RUN} python -m pip install -e .[quality,test]
         ${CONDA_RUN} python -m pip install --pre torch==${MPS_TORCH_VERSION} --extra-index-url https://download.pytorch.org/whl/test/cpu
         ${CONDA_RUN} python -m pip install git+https://github.com/huggingface/accelerate
+        ${CONDA_RUN} python -m pip install -U git+https://github.com/huggingface/transformers
 
     - name: Environment
       shell: arch -arch arm64 bash {0}

diff --git a/.github/workflows/push_tests.yml b/.github/workflows/push_tests.yml
@@ -62,6 +62,7 @@ jobs:
       run: |
         python -m pip install -e .[quality,test]
         python -m pip install git+https://github.com/huggingface/accelerate
+        python -m pip install -U git+https://github.com/huggingface/transformers
 
     - name: Environment
       run: |
@@ -131,6 +132,7 @@ jobs:
       run: |
         python -m pip install -e .[quality,test,training]
         python -m pip install git+https://github.com/huggingface/accelerate
+        python -m pip install -U git+https://github.com/huggingface/transformers
 
     - name: Environment
       run: |

diff --git a/docs/source/api/pipelines/stable_diffusion.mdx b/docs/source/api/pipelines/stable_diffusion.mdx
@@ -88,3 +88,10 @@ If you want to use all possible use cases in a single `DiffusionPipeline` you ca
 	- __call__
 	- enable_attention_slicing
 	- disable_attention_slicing
+
+
+## StableDiffusionImageVariationPipeline
+[[autodoc]] StableDiffusionImageVariationPipeline
+	- __call__
+	- enable_attention_slicing
+	- disable_attention_slicing
diff --git a/src/diffusers/__init__.py b/src/diffusers/__init__.py
@@ -69,6 +69,7 @@
         AltDiffusionPipeline,
         CycleDiffusionPipeline,
         LDMTextToImagePipeline,
+        StableDiffusionImageVariationPipeline,
         StableDiffusionImg2ImgPipeline,
         StableDiffusionInpaintPipeline,
         StableDiffusionInpaintPipelineLegacy,

diff --git a/src/diffusers/pipelines/__init__.py b/src/diffusers/pipelines/__init__.py
@@ -19,6 +19,7 @@
     from .latent_diffusion import LDMTextToImagePipeline
     from .stable_diffusion import (
         CycleDiffusionPipeline,
+        StableDiffusionImageVariationPipeline,
         StableDiffusionImg2ImgPipeline,
         StableDiffusionInpaintPipeline,
         StableDiffusionInpaintPipelineLegacy,

diff --git a/src/diffusers/pipelines/stable_diffusion/__init__.py b/src/diffusers/pipelines/stable_diffusion/__init__.py
@@ -30,6 +30,7 @@ class StableDiffusionPipelineOutput(BaseOutput):
 if is_transformers_available() and is_torch_available():
     from .pipeline_cycle_diffusion import CycleDiffusionPipeline
     from .pipeline_stable_diffusion import StableDiffusionPipeline
+    from .pipeline_stable_diffusion_image_variation import StableDiffusionImageVariationPipeline
     from .pipeline_stable_diffusion_img2img import StableDiffusionImg2ImgPipeline
     from .pipeline_stable_diffusion_inpaint import StableDiffusionInpaintPipeline
     from .pipeline_stable_diffusion_inpaint_legacy import StableDiffusionInpaintPipelineLegacy

diff --git a/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_image_variation.py b/src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_image_variation.py
diff --git a/src/diffusers/utils/dummy_torch_and_transformers_objects.py b/src/diffusers/utils/dummy_torch_and_transformers_objects.py
@@ -64,6 +64,21 @@ def from_pretrained(cls, *args, **kwargs):
         requires_backends(cls, ["torch", "transformers"])
 
 
+class StableDiffusionImageVariationPipeline(metaclass=DummyObject):
+    _backends = ["torch", "transformers"]
+
+    def __init__(self, *args, **kwargs):
+        requires_backends(self, ["torch", "transformers"])
+
+    @classmethod
+    def from_config(cls, *args, **kwargs):
+        requires_backends(cls, ["torch", "transformers"])
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        requires_backends(cls, ["torch", "transformers"])
+
+
 class StableDiffusionImg2ImgPipeline(metaclass=DummyObject):
     _backends = ["torch", "transformers"]