Merge branch 'main' into transormer2d-variants

.github/workflows/nightly_tests.yml

@@ -112,7 +112,7 @@ jobs:
 
   run_nightly_tests_for_other_torch_modules:
     name: Torch Non-Pipelines CUDA Nightly Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
@@ -185,7 +185,7 @@ jobs:
 
   run_lora_nightly_tests:
     name: Nightly LoRA Tests with PEFT and TORCH
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
@@ -298,7 +298,7 @@ jobs:
 
   run_nightly_onnx_tests:
     name: Nightly ONNXRuntime CUDA tests on Ubuntu
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-onnxruntime-cuda
       options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/

.github/workflows/pr_test_fetcher.yml

@@ -15,7 +15,7 @@ concurrency:
 jobs:
   setup_pr_tests:
     name: Setup PR Tests
-    runs-on: docker-cpu
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
     container:
       image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
@@ -73,7 +73,7 @@ jobs:
       max-parallel: 2
       matrix:
         modules: ${{ fromJson(needs.setup_pr_tests.outputs.matrix) }}
-    runs-on: docker-cpu
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
     container:
       image: diffusers/diffusers-pytorch-cpu
       options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
@@ -123,7 +123,7 @@ jobs:
         config:
           - name: Hub tests for models, schedulers, and pipelines
             framework: hub_tests_pytorch
-            runner: docker-cpu
+            runner: [ self-hosted, intel-cpu, 8-cpu, ci ]
             image: diffusers/diffusers-pytorch-cpu
             report: torch_hub
 

.github/workflows/push_tests.yml

@@ -21,22 +21,23 @@ env:
 jobs:
   setup_torch_cuda_pipeline_matrix:
     name: Setup Torch Pipelines CUDA Slow Tests Matrix
-    runs-on: diffusers/diffusers-pytorch-cpu
+    runs-on: [ self-hosted, intel-cpu, 8-cpu, ci ]
+    container:
+      image: diffusers/diffusers-pytorch-cpu
     outputs:
       pipeline_test_matrix: ${{ steps.fetch_pipeline_matrix.outputs.pipeline_test_matrix }}
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
         with:
           fetch-depth: 2
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.8"
       - name: Install dependencies
         run: |
-          pip install -e .
-          pip install huggingface_hub
+          python -m venv /opt/venv && export PATH="/opt/venv/bin:$PATH"
+          python -m uv pip install -e [quality,test]
+      - name: Environment
+        run: |
+          python utils/print_env.py
       - name: Fetch Pipeline Matrix
         id: fetch_pipeline_matrix
         run: |
@@ -60,7 +61,7 @@ jobs:
     runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0 --privileged
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0 --privileged
     steps:
       - name: Checkout diffusers
         uses: actions/checkout@v3
@@ -114,10 +115,10 @@ jobs:
 
   torch_cuda_tests:
     name: Torch CUDA Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
@@ -166,10 +167,10 @@ jobs:
 
   peft_cuda_tests:
     name: PEFT CUDA Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface/diffusers:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
@@ -219,7 +220,7 @@ jobs:
     runs-on: docker-tpu
     container:
       image: diffusers/diffusers-flax-tpu
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --privileged
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --privileged
     defaults:
       run:
         shell: bash
@@ -263,10 +264,10 @@ jobs:
 
   onnx_cuda_tests:
     name: ONNX CUDA Tests
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
     container:
       image: diffusers/diffusers-onnxruntime-cuda
-      options: --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/ --gpus 0
+      options: --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/ --gpus 0
     defaults:
       run:
         shell: bash
@@ -311,11 +312,11 @@ jobs:
   run_torch_compile_tests:
     name: PyTorch Compile CUDA tests
 
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-compile-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -352,11 +353,11 @@ jobs:
   run_xformers_tests:
     name: PyTorch xformers CUDA tests
 
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-xformers-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
     - name: Checkout diffusers
@@ -393,11 +394,11 @@ jobs:
   run_examples_tests:
     name: Examples PyTorch CUDA tests on Ubuntu
 
-    runs-on: docker-gpu
+    runs-on: [single-gpu, nvidia-gpu, t4, ci]
 
     container:
       image: diffusers/diffusers-pytorch-cuda
-      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/hf_cache:/mnt/cache/
+      options: --gpus 0 --shm-size "16gb" --ipc host -v /mnt/cache/.cache/huggingface:/mnt/cache/
 
     steps:
     - name: Checkout diffusers

docs/source/en/_toctree.yml

@@ -81,16 +81,14 @@
     title: ControlNet
   - local: using-diffusers/t2i_adapter
     title: T2I-Adapter
+  - local: using-diffusers/inference_with_lcm
+    title: Latent Consistency Model
   - local: using-diffusers/textual_inversion_inference
     title: Textual inversion
   - local: using-diffusers/shap-e
     title: Shap-E
   - local: using-diffusers/diffedit
     title: DiffEdit
-  - local: using-diffusers/inference_with_lcm_lora
-    title: Latent Consistency Model-LoRA
-  - local: using-diffusers/inference_with_lcm
-    title: Latent Consistency Model
   - local: using-diffusers/inference_with_tcd_lora
     title: Trajectory Consistency Distillation-LoRA
   - local: using-diffusers/svd
@@ -141,8 +139,6 @@
 - sections:
   - local: optimization/fp16
     title: Speed up inference
-  - local: using-diffusers/distilled_sd
-    title: Distilled Stable Diffusion inference
   - local: optimization/memory
     title: Reduce memory usage
   - local: optimization/torch2.0

docs/source/en/api/attnprocessor.md

@@ -55,3 +55,6 @@ An attention processor is a class for applying different types of attention mech
 
 ## XFormersAttnProcessor
 [[autodoc]] models.attention_processor.XFormersAttnProcessor
+
+## AttnProcessorNPU
+[[autodoc]] models.attention_processor.AttnProcessorNPU

docs/source/en/optimization/fp16.md

@@ -12,39 +12,35 @@ specific language governing permissions and limitations under the License.
 
 # Speed up inference
 
-There are several ways to optimize 🤗 Diffusers for inference speed. As a general rule of thumb, we recommend using either [xFormers](xformers) or `torch.nn.functional.scaled_dot_product_attention` in PyTorch 2.0 for their memory-efficient attention.
+There are several ways to optimize Diffusers for inference speed, such as reducing the computational burden by lowering the data precision or using a lightweight distilled model. There are also memory-efficient attention implementations, [xFormers](xformers) and [scaled dot product attetntion](https://pytorch.org/docs/stable/generated/torch.nn.functional.scaled_dot_product_attention.html) in PyTorch 2.0, that reduce memory usage which also indirectly speeds up inference. Different speed optimizations can be stacked together to get the fastest inference times.
 
-<Tip>
+> [!TIP]
+> Optimizing for inference speed or reduced memory usage can lead to improved performance in the other category, so you should try to optimize for both whenever you can. This guide focuses on inference speed, but you can learn more about lowering memory usage in the [Reduce memory usage](memory) guide.
 
-In many cases, optimizing for speed or memory leads to improved performance in the other, so you should try to optimize for both whenever you can. This guide focuses on inference speed, but you can learn more about preserving memory in the [Reduce memory usage](memory) guide.
+The inference times below are obtained from generating a single 512x512 image from the prompt "a photo of an astronaut riding a horse on mars" with 50 DDIM steps on a NVIDIA A100.
 
-</Tip>
+| setup    | latency | speed-up |
+|----------|---------|----------|
+| baseline | 5.27s   | x1       |
+| tf32     | 4.14s   | x1.27    |
+| fp16     | 3.51s   | x1.50    |
+| combined | 3.41s   | x1.54    |
 
-The results below are obtained from generating a single 512x512 image from the prompt `a photo of an astronaut riding a horse on mars` with 50 DDIM steps on a Nvidia Titan RTX, demonstrating the speed-up you can expect.
+## TensorFloat-32
 
-|                  | latency | speed-up |
-| ---------------- | ------- | ------- |
-| original         | 9.50s   | x1      |
-| fp16             | 3.61s   | x2.63   |
-| channels last    | 3.30s   | x2.88   |
-| traced UNet      | 3.21s   | x2.96   |
-| memory efficient attention  | 2.63s  | x3.61   |
-
-## Use TensorFloat-32
-
-On Ampere and later CUDA devices, matrix multiplications and convolutions can use the [TensorFloat-32 (TF32)](https://blogs.nvidia.com/blog/2020/05/14/tensorfloat-32-precision-format/) mode for faster, but slightly less accurate computations. By default, PyTorch enables TF32 mode for convolutions but not matrix multiplications. Unless your network requires full float32 precision, we recommend enabling TF32 for matrix multiplications. It can significantly speeds up computations with typically negligible loss in numerical accuracy.
+On Ampere and later CUDA devices, matrix multiplications and convolutions can use the [TensorFloat-32 (tf32)](https://blogs.nvidia.com/blog/2020/05/14/tensorfloat-32-precision-format/) mode for faster, but slightly less accurate computations. By default, PyTorch enables tf32 mode for convolutions but not matrix multiplications. Unless your network requires full float32 precision, we recommend enabling tf32 for matrix multiplications. It can significantly speed up computations with typically negligible loss in numerical accuracy.
 
 ```python
 import torch
 
 torch.backends.cuda.matmul.allow_tf32 = True
 ```
 
-You can learn more about TF32 in the [Mixed precision training](https://huggingface.co/docs/transformers/en/perf_train_gpu_one#tf32) guide.
+Learn more about tf32 in the [Mixed precision training](https://huggingface.co/docs/transformers/en/perf_train_gpu_one#tf32) guide.
 
 ## Half-precision weights
 
-To save GPU memory and get more speed, try loading and running the model weights directly in half-precision or float16:
+To save GPU memory and get more speed, set `torch_dtype=torch.float16` to load and run the model weights directly with half-precision weights.
 
 ```Python
 import torch
@@ -56,19 +52,76 @@ pipe = DiffusionPipeline.from_pretrained(
     use_safetensors=True,
 )
 pipe = pipe.to("cuda")
-
-prompt = "a photo of an astronaut riding a horse on mars"
-image = pipe(prompt).images[0]
 ```
 
-<Tip warning={true}>
+> [!WARNING]
+> Don't use [torch.autocast](https://pytorch.org/docs/stable/amp.html#torch.autocast) in any of the pipelines as it can lead to black images and is always slower than pure float16 precision.
 
-Don't use [`torch.autocast`](https://pytorch.org/docs/stable/amp.html#torch.autocast) in any of the pipelines as it can lead to black images and is always slower than pure float16 precision.
+## Distilled model
 
-</Tip>
+You could also use a distilled Stable Diffusion model and autoencoder to speed up inference. During distillation, many of the UNet's residual and attention blocks are shed to reduce the model size by 51% and improve latency on CPU/GPU by 43%. The distilled model is faster and uses less memory while generating images of comparable quality to the full Stable Diffusion model.
 
-## Distilled model
+> [!TIP]
+> Read the [Open-sourcing Knowledge Distillation Code and Weights of SD-Small and SD-Tiny](https://huggingface.co/blog/sd_distillation) blog post to learn more about how knowledge distillation training works to produce a faster, smaller, and cheaper generative model.
 
-You could also use a distilled Stable Diffusion model and autoencoder to speed up inference. During distillation, many of the UNet's residual and attention blocks are shed to reduce the model size. The distilled model is faster and uses less memory while generating images of comparable quality to the full Stable Diffusion model.
+The inference times below are obtained from generating 4 images from the prompt "a photo of an astronaut riding a horse on mars" with 25 PNDM steps on a NVIDIA A100. Each generation is repeated 3 times with the distilled Stable Diffusion v1.4 model by [Nota AI](https://hf.co/nota-ai).
+
+| setup                        | latency | speed-up |
+|------------------------------|---------|----------|
+| baseline                     | 6.37s   | x1       |
+| distilled                    | 4.18s   | x1.52    |
+| distilled + tiny autoencoder | 3.83s   | x1.66    |
+
+Let's load the distilled Stable Diffusion model and compare it against the original Stable Diffusion model.
+
+```py
+from diffusers import StableDiffusionPipeline
+import torch
+
+distilled = StableDiffusionPipeline.from_pretrained(
+    "nota-ai/bk-sdm-small", torch_dtype=torch.float16, use_safetensors=True,
+).to("cuda")
+prompt = "a golden vase with different flowers"
+generator = torch.manual_seed(2023)
+image = distilled("a golden vase with different flowers", num_inference_steps=25, generator=generator).images[0]
+image
+```
+
+<div class="flex gap-4">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/original_sd.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">original Stable Diffusion</figcaption>
+  </div>
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/distilled_sd.png"/>
+    <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion</figcaption>
+  </div>
+</div>
+
+### Tiny AutoEncoder
+
+To speed inference up even more, replace the autoencoder with a [distilled version](https://huggingface.co/sayakpaul/taesdxl-diffusers) of it.
+
+```py
+import torch
+from diffusers import AutoencoderTiny, StableDiffusionPipeline
+
+distilled = StableDiffusionPipeline.from_pretrained(
+    "nota-ai/bk-sdm-small", torch_dtype=torch.float16, use_safetensors=True,
+).to("cuda")
+distilled.vae = AutoencoderTiny.from_pretrained(
+    "sayakpaul/taesd-diffusers", torch_dtype=torch.float16, use_safetensors=True,
+).to("cuda")
+
+prompt = "a golden vase with different flowers"
+generator = torch.manual_seed(2023)
+image = distilled("a golden vase with different flowers", num_inference_steps=25, generator=generator).images[0]
+image
+```
 
-Learn more about in the [Distilled Stable Diffusion inference](../using-diffusers/distilled_sd) guide!
+<div class="flex justify-center">
+  <div>
+    <img class="rounded-xl" src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/distilled_sd_vae.png" />
+    <figcaption class="mt-2 text-center text-sm text-gray-500">distilled Stable Diffusion + Tiny AutoEncoder</figcaption>
+  </div>
+</div>