Merge branch 'main' into diff-d2

Author: kashif

.github/workflows/pr_tests.yml

@@ -92,7 +92,6 @@ jobs:
             runner: aws-general-8-plus
             image: diffusers/diffusers-pytorch-cpu
             report: torch_example_cpu
-
     name: ${{ matrix.config.name }}
 
     runs-on:
@@ -115,8 +114,7 @@ jobs:
     - name: Install dependencies
       run: |
         uv pip install -e ".[quality]"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
 
     - name: Environment
@@ -218,8 +216,6 @@ jobs:
 
   run_lora_tests:
     needs: [check_code_quality, check_repository_consistency]
-    strategy:
-      fail-fast: false
 
     name: LoRA tests with PEFT main
 
@@ -247,9 +243,8 @@ jobs:
         uv pip install -U peft@git+https://github.com/huggingface/peft.git --no-deps
         uv pip install -U tokenizers
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git --no-deps
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
-
+        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
+        
     - name: Environment
       run: |
         python utils/print_env.py
@@ -275,6 +270,6 @@ jobs:
       if: ${{ always() }}
       uses: actions/upload-artifact@v6
       with:
-        name: pr_main_test_reports
+        name: pr_lora_test_reports
         path: reports
 

.github/workflows/pr_tests_gpu.yml

@@ -131,8 +131,7 @@ jobs:
         run: |
           uv pip install -e ".[quality]"
           uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+          uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
 
       - name: Environment
         run: |
@@ -202,8 +201,7 @@ jobs:
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
 
     - name: Environment
       run: |
@@ -264,8 +262,7 @@ jobs:
         nvidia-smi
     - name: Install dependencies
       run: |
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
         uv pip install -e ".[quality,training]"
 
     - name: Environment

.github/workflows/push_tests.yml

@@ -76,8 +76,7 @@ jobs:
         run: |
           uv pip install -e ".[quality]"
           uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-          #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-          uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+          uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
       - name: Environment
         run: |
           python utils/print_env.py
@@ -129,8 +128,7 @@ jobs:
         uv pip install -e ".[quality]"
         uv pip install peft@git+https://github.com/huggingface/peft.git
         uv pip uninstall accelerate && uv pip install -U accelerate@git+https://github.com/huggingface/accelerate.git
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
 
     - name: Environment
       run: |
@@ -182,8 +180,7 @@ jobs:
     - name: Install dependencies
       run: |
         uv pip install -e ".[quality,training]"
-        #uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
-        uv pip uninstall transformers huggingface_hub && uv pip install transformers==4.57.1
+        uv pip uninstall transformers huggingface_hub && uv pip install --prerelease allow -U transformers@git+https://github.com/huggingface/transformers.git
     - name: Environment
       run: |
         python utils/print_env.py

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

@@ -46,6 +46,20 @@ output = pipe(
 output.save("output.png")
 ```
 
+## Cosmos2_5_TransferPipeline
+
+[[autodoc]] Cosmos2_5_TransferPipeline
+  - all
+  - __call__
+
+
+## Cosmos2_5_PredictBasePipeline
+
+[[autodoc]] Cosmos2_5_PredictBasePipeline
+  - all
+  - __call__
+
+
 ## CosmosTextToWorldPipeline
 
 [[autodoc]] CosmosTextToWorldPipeline
@@ -70,12 +84,6 @@ output.save("output.png")
   - all
   - __call__
 
-## Cosmos2_5_PredictBasePipeline
-
-[[autodoc]] Cosmos2_5_PredictBasePipeline
-  - all
-  - __call__
-
 ## CosmosPipelineOutput
 
 [[autodoc]] pipelines.cosmos.pipeline_output.CosmosPipelineOutput

docs/source/en/training/distributed_inference.md

@@ -111,7 +111,7 @@ if __name__ == "__main__":
 Call `torchrun` to run the inference script and use the `--nproc_per_node` argument to set the number of GPUs to use.
 
 ```bash
-torchrun run_distributed.py --nproc_per_node=2
+torchrun --nproc_per_node=2 run_distributed.py
 ```
 
 ## device_map

examples/custom_diffusion/test_custom_diffusion.py

@@ -17,6 +17,9 @@
 import os
 import sys
 import tempfile
+import unittest
+
+from diffusers.utils import is_transformers_version
 
 
 sys.path.append("..")
@@ -30,6 +33,7 @@
 logger.addHandler(stream_handler)
 
 
+@unittest.skipIf(is_transformers_version(">=", "4.57.5"), "Size mismatch")
 class CustomDiffusion(ExamplesTestsAccelerate):
     def test_custom_diffusion(self):
         with tempfile.TemporaryDirectory() as tmpdir:

scripts/convert_cosmos_to_diffusers.py

@@ -94,9 +94,15 @@
     --transformer_type Cosmos-2.5-Transfer-General-2B \
     --transformer_ckpt_path $transformer_ckpt_path \
     --vae_type wan2.1 \
-    --output_path converted/transfer/2b/general/depth \
+    --output_path converted/transfer/2b/general/depth/pipeline \
     --save_pipeline
 
+python scripts/convert_cosmos_to_diffusers.py \
+    --transformer_type Cosmos-2.5-Transfer-General-2B \
+    --transformer_ckpt_path $transformer_ckpt_path \
+    --vae_type wan2.1 \
+    --output_path converted/transfer/2b/general/depth/models
+
 # edge
 transformer_ckpt_path=~/.cache/huggingface/hub/models--nvidia--Cosmos-Transfer2.5-2B/snapshots/eb5325b77d358944da58a690157dd2b8071bbf85/general/edge/61f5694b-0ad5-4ecd-8ad7-c8545627d125_ema_bf16.pt
 
@@ -120,18 +126,30 @@
     --transformer_type Cosmos-2.5-Transfer-General-2B \
     --transformer_ckpt_path $transformer_ckpt_path \
     --vae_type wan2.1 \
-    --output_path converted/transfer/2b/general/blur \
+    --output_path converted/transfer/2b/general/blur/pipeline \
     --save_pipeline
 
+python scripts/convert_cosmos_to_diffusers.py \
+    --transformer_type Cosmos-2.5-Transfer-General-2B \
+    --transformer_ckpt_path $transformer_ckpt_path \
+    --vae_type wan2.1 \
+    --output_path converted/transfer/2b/general/blur/models
+
 # seg
 transformer_ckpt_path=~/.cache/huggingface/hub/models--nvidia--Cosmos-Transfer2.5-2B/snapshots/eb5325b77d358944da58a690157dd2b8071bbf85/general/seg/5136ef49-6d8d-42e8-8abf-7dac722a304a_ema_bf16.pt
 
 python scripts/convert_cosmos_to_diffusers.py \
     --transformer_type Cosmos-2.5-Transfer-General-2B \
     --transformer_ckpt_path $transformer_ckpt_path \
     --vae_type wan2.1 \
-    --output_path converted/transfer/2b/general/seg \
+    --output_path converted/transfer/2b/general/seg/pipeline \
     --save_pipeline
+
+python scripts/convert_cosmos_to_diffusers.py \
+    --transformer_type Cosmos-2.5-Transfer-General-2B \
+    --transformer_ckpt_path $transformer_ckpt_path \
+    --vae_type wan2.1 \
+    --output_path converted/transfer/2b/general/seg/models
 ```
 """
 

src/diffusers/hooks/_common.py

@@ -48,6 +48,7 @@
     torch.nn.ConvTranspose2d,
     torch.nn.ConvTranspose3d,
     torch.nn.Linear,
+    torch.nn.Embedding,
     # TODO(aryan): look into torch.nn.LayerNorm, torch.nn.GroupNorm later, seems to be causing some issues with CogVideoX
     # because of double invocation of the same norm layer in CogVideoXLayerNorm
 )

src/diffusers/loaders/lora_conversion_utils.py

@@ -856,7 +856,7 @@ def _convert(original_key, diffusers_key, state_dict, new_state_dict):
                 )
             state_dict = {k: v for k, v in state_dict.items() if not k.startswith("text_encoders.t5xxl.transformer.")}
 
-        has_diffb = any("diff_b" in k and k.startswith(("lora_unet_", "lora_te_")) for k in state_dict)
+        has_diffb = any("diff_b" in k and k.startswith(("lora_unet_", "lora_te_", "lora_te1_")) for k in state_dict)
         if has_diffb:
             zero_status_diff_b = state_dict_all_zero(state_dict, ".diff_b")
             if zero_status_diff_b:
@@ -895,7 +895,7 @@ def _convert(original_key, diffusers_key, state_dict, new_state_dict):
         state_dict = {
             _custom_replace(k, limit_substrings): v
             for k, v in state_dict.items()
-            if k.startswith(("lora_unet_", "lora_te_"))
+            if k.startswith(("lora_unet_", "lora_te_", "lora_te1_"))
         }
 
         if any("text_projection" in k for k in state_dict):

src/diffusers/loaders/lora_pipeline.py

@@ -5472,6 +5472,10 @@ def lora_state_dict(
             logger.warning(warn_msg)
             state_dict = {k: v for k, v in state_dict.items() if "dora_scale" not in k}
 
+        is_peft_format = any(k.startswith("base_model.model.") for k in state_dict)
+        if is_peft_format:
+            state_dict = {k.replace("base_model.model.", "diffusion_model."): v for k, v in state_dict.items()}
+
         is_ai_toolkit = any(k.startswith("diffusion_model.") for k in state_dict)
         if is_ai_toolkit:
             state_dict = _convert_non_diffusers_flux2_lora_to_diffusers(state_dict)