Merge branch 'main' into sd3.5-controlnet

Author: yiyixuxu

.github/workflows/nightly_tests.yml

@@ -347,6 +347,64 @@ jobs:
         pip install slack_sdk tabulate
         python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
 
+  run_nightly_quantization_tests:
+    name: Torch quantization nightly tests
+    strategy:
+      fail-fast: false
+      max-parallel: 2
+      matrix: 
+        config:
+          - backend: "bitsandbytes"
+            test_location: "bnb"
+    runs-on:
+      group: aws-g6e-xlarge-plus
+    container:
+      image: diffusers/diffusers-pytorch-cuda
+      options: --shm-size "20gb" --ipc host --gpus 0
+    steps:
+      - name: Checkout diffusers
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2
+      - name: NVIDIA-SMI
+        run: nvidia-smi
+      - name: Install dependencies
+        run: |
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+          python -m uv pip install -U ${{ matrix.config.backend }}
+          python -m uv pip install pytest-reportlog
+      - name: Environment
+        run: |
+          python utils/print_env.py
+      - name: ${{ matrix.config.backend }} quantization tests on GPU
+        env:
+          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
+          # https://pytorch.org/docs/stable/notes/randomness.html#avoiding-nondeterministic-algorithms
+          CUBLAS_WORKSPACE_CONFIG: :16:8
+          BIG_GPU_MEMORY: 40
+        run: |
+          python -m pytest -n 1 --max-worker-restart=0 --dist=loadfile \
+            --make-reports=tests_${{ matrix.config.backend }}_torch_cuda \
+            --report-log=tests_${{ matrix.config.backend }}_torch_cuda.log \
+            tests/quantization/${{ matrix.config.test_location }}
+      - name: Failure short reports
+        if: ${{ failure() }}
+        run: |
+          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_stats.txt
+          cat reports/tests_${{ matrix.config.backend }}_torch_cuda_failures_short.txt
+      - name: Test suite reports artifacts
+        if: ${{ always() }}
+        uses: actions/upload-artifact@v4
+        with:
+          name: torch_cuda_${{ matrix.config.backend }}_reports
+          path: reports
+      - name: Generate Report and Notify Channel
+        if: always()
+        run: |
+          pip install slack_sdk tabulate
+          python utils/log_reports.py >> $GITHUB_STEP_SUMMARY
+
 # M1 runner currently not well supported
 # TODO: (Dhruv) add these back when we setup better testing for Apple Silicon
 #  run_nightly_tests_apple_m1:

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

@@ -30,15 +30,17 @@ Make sure to check out the Schedulers [guide](../../using-diffusers/schedulers.m
 This pipeline was contributed by [zRzRzRzRzRzRzR](https://github.com/zRzRzRzRzRzRzR). The original codebase can be found [here](https://huggingface.co/THUDM). The original weights can be found under [hf.co/THUDM](https://huggingface.co/THUDM).
 
 There are three official CogVideoX checkpoints for text-to-video and video-to-video.
+
 | checkpoints | recommended inference dtype |
-|---|---|
+|:---:|:---:|
 | [`THUDM/CogVideoX-2b`](https://huggingface.co/THUDM/CogVideoX-2b) | torch.float16 |
 | [`THUDM/CogVideoX-5b`](https://huggingface.co/THUDM/CogVideoX-5b) | torch.bfloat16 |
 | [`THUDM/CogVideoX1.5-5b`](https://huggingface.co/THUDM/CogVideoX1.5-5b) | torch.bfloat16 |
 
 There are two official CogVideoX checkpoints available for image-to-video.
+
 | checkpoints | recommended inference dtype |
-|---|---|
+|:---:|:---:|
 | [`THUDM/CogVideoX-5b-I2V`](https://huggingface.co/THUDM/CogVideoX-5b-I2V) | torch.bfloat16 |
 | [`THUDM/CogVideoX-1.5-5b-I2V`](https://huggingface.co/THUDM/CogVideoX-1.5-5b-I2V) | torch.bfloat16 |
 
@@ -48,8 +50,9 @@ For the CogVideoX 1.5 series:
 - Both T2V and I2V models support generation with 81 and 161 frames and work best at this value. Exporting videos at 16 FPS is recommended.
 
 There are two official CogVideoX checkpoints that support pose controllable generation (by the [Alibaba-PAI](https://huggingface.co/alibaba-pai) team).
+
 | checkpoints | recommended inference dtype |
-|---|---|
+|:---:|:---:|
 | [`alibaba-pai/CogVideoX-Fun-V1.1-2b-Pose`](https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-2b-Pose) | torch.bfloat16 |
 | [`alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose`](https://huggingface.co/alibaba-pai/CogVideoX-Fun-V1.1-5b-Pose) | torch.bfloat16 |
 

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

@@ -22,12 +22,20 @@ Flux can be quite expensive to run on consumer hardware devices. However, you ca
 
 </Tip>
 
-Flux comes in two variants:
+Flux comes in the following variants:
 
-* Timestep-distilled (`black-forest-labs/FLUX.1-schnell`)
-* Guidance-distilled (`black-forest-labs/FLUX.1-dev`)
+| model type | model id |
+|:----------:|:--------:|
+| Timestep-distilled | [`black-forest-labs/FLUX.1-schnell`](https://huggingface.co/black-forest-labs/FLUX.1-schnell) |
+| Guidance-distilled | [`black-forest-labs/FLUX.1-dev`](https://huggingface.co/black-forest-labs/FLUX.1-dev) |
+| Fill Inpainting/Outpainting (Guidance-distilled) | [`black-forest-labs/FLUX.1-Fill-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Fill-dev) |
+| Canny Control (Guidance-distilled) | [`black-forest-labs/FLUX.1-Canny-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev) |
+| Depth Control (Guidance-distilled) | [`black-forest-labs/FLUX.1-Depth-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev) |
+| Canny Control (LoRA) | [`black-forest-labs/FLUX.1-Canny-dev-lora`](https://huggingface.co/black-forest-labs/FLUX.1-Canny-dev-lora) |
+| Depth Control (LoRA) | [`black-forest-labs/FLUX.1-Depth-dev-lora`](https://huggingface.co/black-forest-labs/FLUX.1-Depth-dev-lora) |
+| Redux (Adapter) | [`black-forest-labs/FLUX.1-Redux-dev`](https://huggingface.co/black-forest-labs/FLUX.1-Redux-dev) |
 
-Both checkpoints have slightly difference usage which we detail below.
+All checkpoints have different usage which we detail below.
 
 ### Timestep-distilled
 
@@ -77,7 +85,132 @@ out = pipe(
 out.save("image.png")
 ```
 
+### Fill Inpainting/Outpainting
+
+* Flux Fill pipeline does not require `strength` as an input like regular inpainting pipelines.
+* It supports both inpainting and outpainting.
+
+```python
+import torch
+from diffusers import FluxFillPipeline
+from diffusers.utils import load_image
+
+image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/cup.png")
+mask = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/cup_mask.png")
+
+repo_id = "black-forest-labs/FLUX.1-Fill-dev"
+pipe = FluxFillPipeline.from_pretrained(repo_id, torch_dtype=torch.bfloat16).to("cuda")
+
+image = pipe(
+    prompt="a white paper cup",
+    image=image,
+    mask_image=mask,
+    height=1632,
+    width=1232,
+    max_sequence_length=512,
+    generator=torch.Generator("cpu").manual_seed(0)
+).images[0]
+image.save(f"output.png")
+```
+
+### Canny Control
+
+**Note:** `black-forest-labs/Flux.1-Canny-dev` is _not_ a [`ControlNetModel`] model. ControlNet models are a separate component from the UNet/Transformer whose residuals are added to the actual underlying model. Canny Control is an alternate architecture that achieves effectively the same results as a ControlNet model would, by using channel-wise concatenation with input control condition and ensuring the transformer learns structure control by following the condition as closely as possible. 
+
+```python
+# !pip install -U controlnet-aux
+import torch
+from controlnet_aux import CannyDetector
+from diffusers import FluxControlPipeline
+from diffusers.utils import load_image
+
+pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-Canny-dev", torch_dtype=torch.bfloat16).to("cuda")
+
+prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
+control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
+
+processor = CannyDetector()
+control_image = processor(control_image, low_threshold=50, high_threshold=200, detect_resolution=1024, image_resolution=1024)
+
+image = pipe(
+    prompt=prompt,
+    control_image=control_image,
+    height=1024,
+    width=1024,
+    num_inference_steps=50,
+    guidance_scale=30.0,
+).images[0]
+image.save("output.png")
+```
+
+### Depth Control
+
+**Note:** `black-forest-labs/Flux.1-Depth-dev` is _not_ a ControlNet model. [`ControlNetModel`] models are a separate component from the UNet/Transformer whose residuals are added to the actual underlying model. Depth Control is an alternate architecture that achieves effectively the same results as a ControlNet model would, by using channel-wise concatenation with input control condition and ensuring the transformer learns structure control by following the condition as closely as possible.
+
+```python
+# !pip install git+https://github.com/huggingface/image_gen_aux
+import torch
+from diffusers import FluxControlPipeline, FluxTransformer2DModel
+from diffusers.utils import load_image
+from image_gen_aux import DepthPreprocessor
+
+pipe = FluxControlPipeline.from_pretrained("black-forest-labs/FLUX.1-Depth-dev", torch_dtype=torch.bfloat16).to("cuda")
+
+prompt = "A robot made of exotic candies and chocolates of different kinds. The background is filled with confetti and celebratory gifts."
+control_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/robot.png")
+
+processor = DepthPreprocessor.from_pretrained("LiheYoung/depth-anything-large-hf")
+control_image = processor(control_image)[0].convert("RGB")
+
+image = pipe(
+    prompt=prompt,
+    control_image=control_image,
+    height=1024,
+    width=1024,
+    num_inference_steps=30,
+    guidance_scale=10.0,
+    generator=torch.Generator().manual_seed(42),
+).images[0]
+image.save("output.png")
+```
+
+### Redux
+
+* Flux Redux pipeline is an adapter for FLUX.1 base models. It can be used with both flux-dev and flux-schnell, for image-to-image generation.
+* You can first use the `FluxPriorReduxPipeline` to get the `prompt_embeds` and `pooled_prompt_embeds`, and then feed them into the `FluxPipeline` for image-to-image generation.
+* When use `FluxPriorReduxPipeline` with a base pipeline, you can set `text_encoder=None` and `text_encoder_2=None` in the base pipeline, in order to save VRAM.
+
+```python
+import torch
+from diffusers import FluxPriorReduxPipeline, FluxPipeline
+from diffusers.utils import load_image
+device = "cuda"
+dtype = torch.bfloat16
+
+
+repo_redux = "black-forest-labs/FLUX.1-Redux-dev"
+repo_base = "black-forest-labs/FLUX.1-dev" 
+pipe_prior_redux = FluxPriorReduxPipeline.from_pretrained(repo_redux, torch_dtype=dtype).to(device)
+pipe = FluxPipeline.from_pretrained(
+    repo_base, 
+    text_encoder=None,
+    text_encoder_2=None,
+    torch_dtype=torch.bfloat16
+).to(device)
+
+image = load_image("https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/style_ziggy/img5.png")
+pipe_prior_output = pipe_prior_redux(image)
+images = pipe(
+    guidance_scale=2.5,
+    num_inference_steps=50,
+    generator=torch.Generator("cpu").manual_seed(0),
+    **pipe_prior_output,
+).images
+images[0].save("flux-redux.png")
+```
+
 ## Running FP16 inference
+
 Flux can generate high-quality images with FP16 (i.e. to accelerate inference on Turing/Volta GPUs) but produces different outputs compared to FP32/BF16. The issue is that some activations in the text encoders have to be clipped when running in FP16, which affects the overall image. Forcing text encoders to run with FP32 inference thus removes this output difference. See [here](https://github.com/huggingface/diffusers/pull/9097#issuecomment-2272292516) for details.
 
 FP16 inference code:
@@ -188,3 +321,27 @@ image.save("flux-fp8-dev.png")
 [[autodoc]] FluxControlNetImg2ImgPipeline
 	- all
 	- __call__
+
+## FluxControlPipeline
+
+[[autodoc]] FluxControlPipeline
+	- all
+	- __call__
+
+## FluxControlImg2ImgPipeline
+
+[[autodoc]] FluxControlImg2ImgPipeline
+	- all
+	- __call__
+
+## FluxPriorReduxPipeline
+
+[[autodoc]] FluxPriorReduxPipeline
+	- all
+	- __call__
+
+## FluxFillPipeline
+
+[[autodoc]] FluxFillPipeline
+	- all
+	- __call__

docs/source/en/conceptual/evaluation.md

@@ -181,7 +181,7 @@ Then we load the [v1-5 checkpoint](https://huggingface.co/stable-diffusion-v1-5/
 
 ```python
 model_ckpt_1_5 = "stable-diffusion-v1-5/stable-diffusion-v1-5"
-sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=weight_dtype).to(device)
+sd_pipeline_1_5 = StableDiffusionPipeline.from_pretrained(model_ckpt_1_5, torch_dtype=torch.float16).to("cuda")
 
 images_1_5 = sd_pipeline_1_5(prompts, num_images_per_prompt=1, generator=generator, output_type="np").images
 ```
@@ -280,7 +280,7 @@ from diffusers import StableDiffusionInstructPix2PixPipeline
 
 instruct_pix2pix_pipeline = StableDiffusionInstructPix2PixPipeline.from_pretrained(
     "timbrooks/instruct-pix2pix", torch_dtype=torch.float16
-).to(device)
+).to("cuda")
 ```
 
 Now, we perform the edits:
@@ -326,9 +326,9 @@ from transformers import (
 
 clip_id = "openai/clip-vit-large-patch14"
 tokenizer = CLIPTokenizer.from_pretrained(clip_id)
-text_encoder = CLIPTextModelWithProjection.from_pretrained(clip_id).to(device)
+text_encoder = CLIPTextModelWithProjection.from_pretrained(clip_id).to("cuda")
 image_processor = CLIPImageProcessor.from_pretrained(clip_id)
-image_encoder = CLIPVisionModelWithProjection.from_pretrained(clip_id).to(device)
+image_encoder = CLIPVisionModelWithProjection.from_pretrained(clip_id).to("cuda")
 ```
 
 Notice that we are using a particular CLIP checkpoint, i.e., `openai/clip-vit-large-patch14`. This is because the Stable Diffusion pre-training was performed with this CLIP variant. For more details, refer to the [documentation](https://huggingface.co/docs/transformers/model_doc/clip).
@@ -350,7 +350,7 @@ class DirectionalSimilarity(nn.Module):
 
     def preprocess_image(self, image):
         image = self.image_processor(image, return_tensors="pt")["pixel_values"]
-        return {"pixel_values": image.to(device)}
+        return {"pixel_values": image.to("cuda")}
 
     def tokenize_text(self, text):
         inputs = self.tokenizer(
@@ -360,7 +360,7 @@ class DirectionalSimilarity(nn.Module):
             truncation=True,
             return_tensors="pt",
         )
-        return {"input_ids": inputs.input_ids.to(device)}
+        return {"input_ids": inputs.input_ids.to("cuda")}
 
     def encode_image(self, image):
         preprocessed_image = self.preprocess_image(image)
@@ -459,6 +459,7 @@ with ZipFile(local_filepath, "r") as zipper:
 ```python
 from PIL import Image
 import os
+import numpy as np
 
 dataset_path = "sample-imagenet-images"
 image_paths = sorted([os.path.join(dataset_path, x) for x in os.listdir(dataset_path)])
@@ -477,6 +478,7 @@ Now that the images are loaded, let's apply some lightweight pre-processing on t
 
 ```python
 from torchvision.transforms import functional as F
+import torch
 
 
 def preprocess_image(image):
@@ -498,6 +500,10 @@ dit_pipeline = DiTPipeline.from_pretrained("facebook/DiT-XL-2-256", torch_dtype=
 dit_pipeline.scheduler = DPMSolverMultistepScheduler.from_config(dit_pipeline.scheduler.config)
 dit_pipeline = dit_pipeline.to("cuda")
 
+seed = 0
+generator = torch.manual_seed(seed)
+
+
 words = [
     "cassette player",
     "chainsaw",

docs/source/en/training/create_dataset.md

@@ -1,6 +1,6 @@
 # Create a dataset for training
 
-There are many datasets on the [Hub](https://huggingface.co/datasets?task_categories=task_categories:text-to-image&sort=downloads) to train a model on, but if you can't find one you're interested in or want to use your own, you can create a dataset with the 🤗 [Datasets](hf.co/docs/datasets) library. The dataset structure depends on the task you want to train your model on. The most basic dataset structure is a directory of images for tasks like unconditional image generation. Another dataset structure may be a directory of images and a text file containing their corresponding text captions for tasks like text-to-image generation.
+There are many datasets on the [Hub](https://huggingface.co/datasets?task_categories=task_categories:text-to-image&sort=downloads) to train a model on, but if you can't find one you're interested in or want to use your own, you can create a dataset with the 🤗 [Datasets](https://huggingface.co/docs/datasets) library. The dataset structure depends on the task you want to train your model on. The most basic dataset structure is a directory of images for tasks like unconditional image generation. Another dataset structure may be a directory of images and a text file containing their corresponding text captions for tasks like text-to-image generation.
 
 This guide will show you two ways to create a dataset to finetune on:
 
@@ -87,4 +87,4 @@ accelerate launch --mixed_precision="fp16"  train_text_to_image.py \
 
 Now that you've created a dataset, you can plug it into the `train_data_dir` (if your dataset is local) or `dataset_name` (if your dataset is on the Hub) arguments of a training script.
 
-For your next steps, feel free to try and use your dataset to train a model for [unconditional generation](unconditional_training) or [text-to-image generation](text2image)!
+For your next steps, feel free to try and use your dataset to train a model for [unconditional generation](unconditional_training) or [text-to-image generation](text2image)!

docs/source/ko/api/pipelines/stable_diffusion/stable_diffusion_xl.md

@@ -121,7 +121,7 @@ image = pipe(prompt=prompt, image=init_image, mask_image=mask_image, num_inferen
 
 ### 이미지 결과물을 정제하기
 
-[base 모델 체크포인트](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)에서, StableDiffusion-XL 또한 고주파 품질을 향상시키는 이미지를 생성하기 위해 낮은 노이즈 단계 이미지를 제거하는데 특화된 [refiner 체크포인트](huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0)를 포함하고 있습니다. 이 refiner 체크포인트는 이미지 품질을 향상시키기 위해 base 체크포인트를 실행한 후 "두 번째 단계" 파이프라인에 사용될 수 있습니다.
+[base 모델 체크포인트](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0)에서, StableDiffusion-XL 또한 고주파 품질을 향상시키는 이미지를 생성하기 위해 낮은 노이즈 단계 이미지를 제거하는데 특화된 [refiner 체크포인트](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0)를 포함하고 있습니다. 이 refiner 체크포인트는 이미지 품질을 향상시키기 위해 base 체크포인트를 실행한 후 "두 번째 단계" 파이프라인에 사용될 수 있습니다.
 
 refiner를 사용할 때, 쉽게 사용할 수 있습니다
 - 1.) base 모델과 refiner을 사용하는데, 이는 *Denoisers의 앙상블*을 위한 첫 번째 제안된 [eDiff-I](https://research.nvidia.com/labs/dir/eDiff-I/)를 사용하거나
@@ -215,7 +215,7 @@ image = refiner(
 
 #### 2.) 노이즈가 완전히 제거된 기본 이미지에서 이미지 출력을 정제하기
 
-일반적인 [`StableDiffusionImg2ImgPipeline`] 방식에서, 기본 모델에서 생성된 완전히 노이즈가 제거된 이미지는 [refiner checkpoint](huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0)를 사용해 더 향상시킬 수 있습니다.
+일반적인 [`StableDiffusionImg2ImgPipeline`] 방식에서, 기본 모델에서 생성된 완전히 노이즈가 제거된 이미지는 [refiner checkpoint](https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0)를 사용해 더 향상시킬 수 있습니다.
 
 이를 위해, 보통의 "base" text-to-image 파이프라인을 수행 후에 image-to-image 파이프라인으로써 refiner를 실행시킬 수 있습니다. base 모델의 출력을 잠재 공간에 남겨둘 수 있습니다.