Is DDUF format supported?

[nitinmukesh]

I checked this PR, #10037 and it is merged

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "DDUF/FLUX.1-dev-DDUF", dduf_file="FLUX.1-dev.dduf", torch_dtype=torch.bfloat16
)

image = pipe(
    "photo a cat holding a sign that says Diffusers", num_inference_steps=50, guidance_scale=3.5
).images[0]
image.save("cat.png")

(venv) C:\aiOWN\diffuser_webui>python FLUX_DDUF.py
Fetching 1 files: 100%|█████████████████████████████████████████████████████| 1/1 [00:00<?, ?it/s]
Loading state_dict: 100%|███████████████████████████████████████████| 2/2 [00:32<00:00, 16.05s/it]
Loading pipeline components...:  29%|████████▊                      | 2/7 [00:34<01:10, 14.12s/it]You set `add_prefix_space`. The tokenizer needs to be converted from the slow tokenizers
Loading pipeline components...:  57%|█████████████████▋             | 4/7 [00:34<00:26,  8.73s/it]
Traceback (most recent call last):
  File "C:\aiOWN\diffuser_webui\FLUX_DDUF.py", line 4, in <module>
    pipe = DiffusionPipeline.from_pretrained(
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 951, in from_pretrained
    loaded_sub_model = load_sub_model(
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\diffusers\pipelines\pipeline_loading_utils.py", line 742, in load_sub_model
    loaded_sub_model = load_method(name, **loading_kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\diffusers\models\modeling_utils.py", line 931, in from_pretrained
    model_file = _merge_sharded_checkpoints(
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\diffusers\models\model_loading_utils.py", line 365, in _merge_sharded_checkpoints
    raise FileNotFoundError(f"Part file {file_name} not found.")
FileNotFoundError: Part file diffusion_pytorch_model-00003-of-00003.safetensors not found.

- 🤗 Diffusers version: 0.33.0.dev0
- Platform: Windows-10-10.0.26100-SP0
- Running on Google Colab?: No
- Python version: 3.10.11
- PyTorch version (GPU?): 2.5.1+cu124 (True)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Huggingface_hub version: 0.27.1
- Transformers version: 4.48.1
- Accelerate version: 1.4.0.dev0
- PEFT version: 0.14.1.dev0
- Bitsandbytes version: 0.45.1
- Safetensors version: 0.5.2
- xFormers version: not installed
- Accelerator: NVIDIA GeForce RTX 4060 Laptop GPU, 8188 MiB
- Using GPU in script?: <fill in>
- Using distributed or parallel set-up in script?: <fill in>
- 

[a-r-r-o-w]

cc @SunMarc @sayakpaul

[sayakpaul]

Was able to run on a Linux machine as is (except for the direct device placement):

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained(
    "DDUF/FLUX.1-dev-DDUF", dduf_file="FLUX.1-dev.dduf", torch_dtype=torch.bfloat16
).to("cuda")

image = pipe(
    "photo a cat holding a sign that says Diffusers", num_inference_steps=50, guidance_scale=3.5
).images[0]
image.save("cat.png")

Could you ensure your diffusers is installed from the latest main? The code shouldn't reach the path:

model_file = _merge_sharded_checkpoints(

[nitinmukesh]

Not tested.
Not an important feature for now, hence closing.

[julien-c]

snippet from @sayakpaul works for me