Merge branch 'main' into variant-tests

Author: sayakpaul

docs/source/en/api/loaders/single_file.md

@@ -22,9 +22,6 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 
 ## Supported pipelines
 
-- [`CogVideoXPipeline`]
-- [`CogVideoXImageToVideoPipeline`]
-- [`CogVideoXVideoToVideoPipeline`]
 - [`StableDiffusionPipeline`]
 - [`StableDiffusionImg2ImgPipeline`]
 - [`StableDiffusionInpaintPipeline`]
@@ -52,7 +49,6 @@ The [`~loaders.FromSingleFileMixin.from_single_file`] method allows you to load:
 - [`UNet2DConditionModel`]
 - [`StableCascadeUNet`]
 - [`AutoencoderKL`]
-- [`AutoencoderKLCogVideoX`]
 - [`ControlNetModel`]
 - [`SD3Transformer2DModel`]
 - [`FluxTransformer2DModel`]

docs/source/en/api/pipelines/flux.md

@@ -175,3 +175,16 @@ image.save("flux-fp8-dev.png")
 [[autodoc]] FluxInpaintPipeline
 	- all
 	- __call__
+
+
+## FluxControlNetInpaintPipeline
+
+[[autodoc]] FluxControlNetInpaintPipeline
+	- all
+	- __call__
+
+## FluxControlNetImg2ImgPipeline
+
+[[autodoc]] FluxControlNetImg2ImgPipeline
+	- all
+	- __call__

examples/community/README.md

@@ -50,6 +50,7 @@ Please also check out our [Community Scripts](https://github.com/huggingface/dif
 | Stable Diffusion XL Long Weighted Prompt Pipeline | A pipeline support unlimited length of prompt and negative prompt, use A1111 style of prompt weighting | [Stable Diffusion XL Long Weighted Prompt Pipeline](#stable-diffusion-xl-long-weighted-prompt-pipeline) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1LsqilswLR40XLLcp6XFOl5nKb_wOe26W?usp=sharing) | [Andrew Zhu](https://xhinker.medium.com/) |
 | FABRIC - Stable Diffusion with feedback Pipeline | pipeline supports feedback from liked and disliked images | [Stable Diffusion Fabric Pipeline](#stable-diffusion-fabric-pipeline) | - | [Shauray Singh](https://shauray8.github.io/about_shauray/) |
 | sketch inpaint - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion Pipeline](#stable-diffusion-masked-im2im) | - | [Anatoly Belikov](https://github.com/noskill) |
+| sketch inpaint xl - Inpainting with non-inpaint Stable Diffusion | sketch inpaint much like in automatic1111 | [Masked Im2Im Stable Diffusion XL Pipeline](#stable-diffusion-xl-masked-im2im) | - | [Anatoly Belikov](https://github.com/noskill) |
 | prompt-to-prompt | change parts of a prompt and retain image structure (see [paper page](https://prompt-to-prompt.github.io/)) | [Prompt2Prompt Pipeline](#prompt2prompt-pipeline) | - | [Umer H. Adil](https://twitter.com/UmerHAdil) |
 |   Latent Consistency Pipeline                                                                                                    | Implementation of [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://arxiv.org/abs/2310.04378)                                                                                                                                                                                                                                                                                                                                                                                                                                      | [Latent Consistency Pipeline](#latent-consistency-pipeline)      | - |              [Simian Luo](https://github.com/luosiallen) |
 |   Latent Consistency Img2img Pipeline                                                                                                    | Img2img pipeline for Latent Consistency Models                                                                                                                                                                                                                                                                                                                                                                                                                                    | [Latent Consistency Img2Img Pipeline](#latent-consistency-img2img-pipeline)      | - |              [Logan Zoellner](https://github.com/nagolinc) |
@@ -2581,15 +2582,52 @@ result.images[0].save("result.png")
 
 original image mech.png
 
-<img src=<https://github.com/noskill/diffusers/assets/733626/10ad972d-d655-43cb-8de1-039e3d79e849> width="25%" >
+<img src=https://github.com/noskill/diffusers/assets/733626/10ad972d-d655-43cb-8de1-039e3d79e849 width="25%" >
 
 image with mask mech_painted.png
 
-<img src=<https://github.com/noskill/diffusers/assets/733626/c334466a-67fe-4377-9ff7-f46021b9c224> width="25%" >
+<img src=https://github.com/noskill/diffusers/assets/733626/c334466a-67fe-4377-9ff7-f46021b9c224 width="25%" >
 
 result:
 
-<img src=<https://github.com/noskill/diffusers/assets/733626/23a0a71d-51db-471e-926a-107ac62512a8> width="25%" >
+<img src=https://github.com/noskill/diffusers/assets/733626/23a0a71d-51db-471e-926a-107ac62512a8 width="25%" >
+
+### Masked Im2Im Stable Diffusion Pipeline XL
+
+This pipeline implements sketch inpaint feature from A1111 for non-inpaint models. The following code reads two images, original and one with mask painted over it. It computes mask as a difference of two images and does the inpainting in the area defined by the mask. Latent code is initialized from the image with the mask by default so the color of the mask affects the result.
+
+```
+img = PIL.Image.open("./mech.png")
+# read image with mask painted over
+img_paint = PIL.Image.open("./mech_painted.png")
+
+pipeline = MaskedStableDiffusionXLImg2ImgPipeline.from_pretrained("frankjoshua/juggernautXL_v8Rundiffusion", dtype=torch.float16)
+
+pipeline.to('cuda')
+pipeline.enable_xformers_memory_efficient_attention()
+
+prompt = "a mech warrior wearing a mask"
+seed = 8348273636437
+for i in range(10):
+    generator = torch.Generator(device="cuda").manual_seed(seed + i)
+    print(seed + i)
+    result = pipeline(prompt=prompt, blur=48, image=img_paint, original_image=img, strength=0.9,
+                          generator=generator, num_inference_steps=60, num_images_per_prompt=1)
+    im = result.images[0]
+    im.save(f"result{i}.png")
+```
+
+original image mech.png
+
+<img src=https://github.com/noskill/diffusers/assets/733626/10ad972d-d655-43cb-8de1-039e3d79e849 width="25%" >
+
+image with mask mech_painted.png
+
+<img src=https://github.com/noskill/diffusers/assets/733626/c334466a-67fe-4377-9ff7-f46021b9c224 width="25%" >
+
+result: 
+
+<img src=https://github.com/noskill/diffusers/assets/733626/5043fb57-a785-4606-a5ba-a36704f7cb42 width="25%" >
 
 ### Prompt2Prompt Pipeline