Merge branch 'main' into fix-chrono-edit-cp

Author: DefTruth

.github/workflows/nightly_tests.yml

@@ -84,7 +84,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             --report-log=tests_pipeline_${{ matrix.module }}_cuda.log \
             tests/pipelines/${{ matrix.module }}
@@ -138,7 +138,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           --report-log=tests_torch_${{ matrix.module }}_cuda.log \
           tests/${{ matrix.module }}
@@ -151,7 +151,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v --make-reports=examples_torch_cuda \
+          --make-reports=examples_torch_cuda \
           --report-log=examples_torch_cuda.log \
           examples/
 
@@ -198,7 +198,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -293,7 +293,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_torch_minimum_version_cuda \
             tests/models/test_modeling_common.py \
             tests/pipelines/test_pipelines_common.py \
@@ -531,7 +531,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} pytest -n 1 -s -v --make-reports=tests_torch_mps \
+#          ${CONDA_RUN} pytest -n 1 --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
 #            tests/
 #      - name: Failure short reports
@@ -587,7 +587,7 @@ jobs:
 #          HF_HOME: /System/Volumes/Data/mnt/cache
 #          HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
 #        run: |
-#          ${CONDA_RUN} pytest -n 1 -s -v --make-reports=tests_torch_mps \
+#          ${CONDA_RUN} pytest -n 1 --make-reports=tests_torch_mps \
 #            --report-log=tests_torch_mps.log \
 #            tests/
 #      - name: Failure short reports

.github/workflows/pr_modular_tests.yml

@@ -120,7 +120,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/modular_pipelines
 

.github/workflows/pr_tests.yml

@@ -126,15 +126,15 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch_pipelines' }}
       run: |
         pytest -n 8 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/pipelines
 
     - name: Run fast PyTorch Model Scheduler CPU tests
       if: ${{ matrix.config.framework == 'pytorch_models' }}
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx and not Dependency" \
+          -k "not Flax and not Onnx and not Dependency" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/models tests/schedulers tests/others
 
@@ -255,11 +255,11 @@ jobs:
     - name: Run fast PyTorch LoRA tests with PEFT
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+          \
           --make-reports=tests_peft_main \
           tests/lora/
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v \
+          \
           --make-reports=tests_models_lora_peft_main \
           tests/models/ -k "lora"
 

.github/workflows/pr_tests_gpu.yml

@@ -151,13 +151,13 @@ jobs:
         run: |
           if [ "${{ matrix.module }}" = "ip_adapters" ]; then 
               pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx" \
+              -k "not Flax and not Onnx" \
               --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
               tests/pipelines/${{ matrix.module }}
           else 
               pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
               pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-              -s -v -k "not Flax and not Onnx and $pattern" \
+              -k "not Flax and not Onnx and $pattern" \
               --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
               tests/pipelines/${{ matrix.module }}
           fi 
@@ -222,10 +222,10 @@ jobs:
       run: |
         pattern=$(cat ${{ steps.extract_tests.outputs.pattern_file }})
         if [ -z "$pattern" ]; then
-          pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
+          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx" tests/${{ matrix.module }} \
           --make-reports=tests_torch_cuda_${{ matrix.module }}  
         else
-          pytest -n 1 -sv --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
+          pytest -n 1  --max-worker-restart=0 --dist=loadfile -k "not Flax and not Onnx and $pattern" tests/${{ matrix.module }} \
           --make-reports=tests_torch_cuda_${{ matrix.module }}  
         fi
 
@@ -274,7 +274,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}

.github/workflows/push_tests.yml

@@ -87,7 +87,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -141,7 +141,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_cuda_${{ matrix.module }} \
           tests/${{ matrix.module }}
 
@@ -189,7 +189,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -230,7 +230,7 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_xformers_cuda_failures_short.txt
@@ -273,7 +273,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}

.github/workflows/push_tests_fast.yml

@@ -70,7 +70,7 @@ jobs:
       if: ${{ matrix.config.framework == 'pytorch' }}
       run: |
         pytest -n 4 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_${{ matrix.config.report }} \
           tests/
 

.github/workflows/push_tests_mps.yml

@@ -57,7 +57,7 @@ jobs:
         HF_HOME: /System/Volumes/Data/mnt/cache
         HF_TOKEN: ${{ secrets.HF_TOKEN }}
       run: |
-        ${CONDA_RUN} python -m pytest -n 0 -s -v --make-reports=tests_torch_mps tests/
+        ${CONDA_RUN} python -m pytest -n 0 --make-reports=tests_torch_mps tests/
 
     - name: Failure short reports
       if: ${{ failure() }}

.github/workflows/release_tests_fast.yml

@@ -84,7 +84,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_pipeline_${{ matrix.module }}_cuda \
             tests/pipelines/${{ matrix.module }}
       - name: Failure short reports
@@ -137,7 +137,7 @@ jobs:
         CUBLAS_WORKSPACE_CONFIG: :16:8
       run: |
         pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-          -s -v -k "not Flax and not Onnx" \
+          -k "not Flax and not Onnx" \
           --make-reports=tests_torch_${{ matrix.module }}_cuda \
           tests/${{ matrix.module }}
 
@@ -187,7 +187,7 @@ jobs:
           CUBLAS_WORKSPACE_CONFIG: :16:8
         run: |
           pytest -n 1 --max-worker-restart=0 --dist=loadfile \
-            -s -v -k "not Flax and not Onnx" \
+            -k "not Flax and not Onnx" \
             --make-reports=tests_torch_minimum_cuda \
             tests/models/test_modeling_common.py \
             tests/pipelines/test_pipelines_common.py \
@@ -240,7 +240,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
         RUN_COMPILE: yes
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "compile" --make-reports=tests_torch_compile_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "compile" --make-reports=tests_torch_compile_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_compile_cuda_failures_short.txt
@@ -281,7 +281,7 @@ jobs:
       env:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile -k "xformers" --make-reports=tests_torch_xformers_cuda tests/
     - name: Failure short reports
       if: ${{ failure() }}
       run: cat reports/tests_torch_xformers_cuda_failures_short.txt
@@ -326,7 +326,7 @@ jobs:
         HF_TOKEN: ${{ secrets.DIFFUSERS_HF_HUB_READ_TOKEN }}
       run: |
         uv pip install ".[training]"
-        pytest -n 1 --max-worker-restart=0 --dist=loadfile -s -v --make-reports=examples_torch_cuda examples/
+        pytest -n 1 --max-worker-restart=0 --dist=loadfile --make-reports=examples_torch_cuda examples/
 
     - name: Failure short reports
       if: ${{ failure() }}

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

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License. -->
 
-# SanaVideoPipeline
+# Sana-Video
 
 <div class="flex flex-wrap space-x-1">
   <img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"/>
@@ -37,6 +37,85 @@ Refer to [this](https://huggingface.co/collections/Efficient-Large-Model/sana-vi
 
 Note: The recommended dtype mentioned is for the transformer weights. The text encoder and VAE weights must stay in `torch.bfloat16` or `torch.float32` for the model to work correctly. Please refer to the inference example below to see how to load the model with the recommended dtype. 
 
+
+## Generation Pipelines
+
+<hfoptions id="generation pipelines">`
+<hfoption id="Text-to-Video">
+
+The example below demonstrates how to use the text-to-video pipeline to generate a video using a text descriptio and a starting frame.
+
+```python
+model_id = 
+pipe = SanaVideoPipeline.from_pretrained("Efficient-Large-Model/SANA-Video_2B_480p_diffusers", torch_dtype=torch.bfloat16)
+pipe.text_encoder.to(torch.bfloat16)
+pipe.vae.to(torch.float32)
+pipe.to("cuda")
+
+prompt = "A cat and a dog baking a cake together in a kitchen. The cat is carefully measuring flour, while the dog is stirring the batter with a wooden spoon. The kitchen is cozy, with sunlight streaming through the window."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_scale = 30
+motion_prompt = f" motion score: {motion_scale}."
+prompt = prompt + motion_prompt
+
+video = pipe(
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    frames=81,
+    guidance_scale=6,
+    num_inference_steps=50,
+    generator=torch.Generator(device="cuda").manual_seed(0),
+).frames[0]
+
+export_to_video(video, "sana_video.mp4", fps=16)
+```
+
+</hfoption>
+<hfoption id="Image-to-Video">
+
+The example below demonstrates how to use the image-to-video pipeline to generate a video using a text descriptio and a starting frame.
+
+```python
+model_id = "Efficient-Large-Model/SANA-Video_2B_480p_diffusers"
+pipe = SanaImageToVideoPipeline.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+)
+pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(pipe.scheduler.config, flow_shift=8.0)
+pipe.vae.to(torch.float32)
+pipe.text_encoder.to(torch.bfloat16)
+pipe.to("cuda")
+
+image = load_image("https://raw.githubusercontent.com/NVlabs/Sana/refs/heads/main/asset/samples/i2v-1.png")
+prompt = "A woman stands against a stunning sunset backdrop, her long, wavy brown hair gently blowing in the breeze. She wears a sleeveless, light-colored blouse with a deep V-neckline, which accentuates her graceful posture. The warm hues of the setting sun cast a golden glow across her face and hair, creating a serene and ethereal atmosphere. The background features a blurred landscape with soft, rolling hills and scattered clouds, adding depth to the scene. The camera remains steady, capturing the tranquil moment from a medium close-up angle."
+negative_prompt = "A chaotic sequence with misshapen, deformed limbs in heavy motion blur, sudden disappearance, jump cuts, jerky movements, rapid shot changes, frames out of sync, inconsistent character shapes, temporal artifacts, jitter, and ghosting effects, creating a disorienting visual experience."
+motion_scale = 30
+motion_prompt = f" motion score: {motion_scale}."
+prompt = prompt + motion_prompt
+
+motion_scale = 30.0
+
+video = pipe(
+    image=image,
+    prompt=prompt,
+    negative_prompt=negative_prompt,
+    height=480,
+    width=832,
+    frames=81,
+    guidance_scale=6,
+    num_inference_steps=50,
+    generator=torch.Generator(device="cuda").manual_seed(0),
+).frames[0]
+
+export_to_video(video, "sana-i2v.mp4", fps=16)
+```
+
+</hfoption>
+</hfoptions>
+
+
 ## Quantization
 
 Quantization helps reduce the memory requirements of very large models by storing model weights in a lower precision data type. However, quantization may have varying impact on video quality depending on the video model.
@@ -97,6 +176,13 @@ export_to_video(output, "sana-video-output.mp4", fps=16)
   - __call__
 
 
+## SanaImageToVideoPipeline
+
+[[autodoc]] SanaImageToVideoPipeline
+  - all
+  - __call__
+
+
 ## SanaVideoPipelineOutput
 
-[[autodoc]] pipelines.sana.pipeline_sana_video.SanaVideoPipelineOutput
+[[autodoc]] pipelines.sana_video.pipeline_sana_video.SanaVideoPipelineOutput

scripts/convert_sana_video_to_diffusers.py

@@ -80,6 +80,8 @@ def main(args):
 
     # scheduler
     flow_shift = 8.0
+    if args.task == "i2v":
+        assert args.scheduler_type == "flow-euler", "Scheduler type must be flow-euler for i2v task."
 
     # model config
     layer_num = 20
@@ -312,6 +314,7 @@ def main(args):
         choices=["flow-dpm_solver", "flow-euler", "uni-pc"],
         help="Scheduler type to use.",
     )
+    parser.add_argument("--task", default="t2v", type=str, required=True, help="Task to convert, t2v or i2v.")
     parser.add_argument("--dump_path", default=None, type=str, required=True, help="Path to the output pipeline.")
     parser.add_argument("--save_full_pipeline", action="store_true", help="save all the pipeline elements in one.")
     parser.add_argument("--dtype", default="fp32", type=str, choices=["fp32", "fp16", "bf16"], help="Weight dtype.")