BestWishYsh

/

Helios-Distilled

like 35

I tried to run the example code given the repo:

import torch
from diffusers import ModularPipeline, ClassifierFreeGuidance
from diffusers.utils import export_to_video, load_image, load_video

mod_pipe = ModularPipeline.from_pretrained("BestWishYsh/Helios-Distilled")
mod_pipe.load_components(torch_dtype=torch.bfloat16)
mod_pipe.to("cuda")

# we need to upload guider to the model repo, so each checkpoint will be able to config their guidance differently
guider = ClassifierFreeGuidance(guidance_scale=1.0)
mod_pipe.update_components(guider=guider)

# --- T2V ---
print("=== T2V ===")
prompt = (
    "A vibrant tropical fish swimming gracefully among colorful coral reefs in a clear, turquoise ocean. "
    "The fish has bright blue and yellow scales with a small, distinctive orange spot on its side, its fins moving "
    "fluidly. The coral reefs are alive with a variety of marine life, including small schools of colorful fish and "
    "sea turtles gliding by. The water is crystal clear, allowing for a view of the sandy ocean floor below. The reef "
    "itself is adorned with a mix of hard and soft corals in shades of red, orange, and green. The photo captures "
    "the fish from a slightly elevated angle, emphasizing its lively movements and the vivid colors of its surroundings. "
    "A close-up shot with dynamic movement."
)

output = mod_pipe(
    prompt=prompt,
    height=384,
    width=640,
    num_frames=240,
    pyramid_num_inference_steps_list=[2, 2, 2],
    is_amplify_first_chunk=True,
    generator=torch.Generator("cuda").manual_seed(42),
    output="videos",
)

export_to_video(output[0], "helios_distilled_modular_t2v_output.mp4", fps=24)
print(f"T2V max memory: {torch.cuda.max_memory_allocated() / 1024**3:.3f} GB")
torch.cuda.empty_cache()
torch.cuda.reset_peak_memory_stats()

But I get the following error:

(backend) unpriv@spark-4626:~/projects/KeyWest3_ImageGeneration/backend$ uv run helios.py 
Uninstalled 1 package in 0.35ms
Installed 1 package in 2ms
Modular Diffusers is currently an experimental feature under active development. The API is subject to breaking changes in future releases.
/home/unpriv/projects/KeyWest3_ImageGeneration/backend/.venv/lib/python3.13/site-packages/huggingface_hub/utils/_validators.py:202: UserWarning: The `local_dir_use_symlinks` argument is deprecated and ignored in `hf_hub_download`. Downloading to a local directory does not use symlinks anymore.
  warnings.warn(
Traceback (most recent call last):
  File "/home/unpriv/projects/KeyWest3_ImageGeneration/backend/helios.py", line 5, in <module>
    mod_pipe = ModularPipeline.from_pretrained("BestWishYsh/Helios-Distilled")
  File "/home/unpriv/projects/KeyWest3_ImageGeneration/backend/.venv/lib/python3.13/site-packages/huggingface_hub/utils/_validators.py", line 89, in _inner_fn
    return fn(*args, **kwargs)
  File "/home/unpriv/projects/KeyWest3_ImageGeneration/backend/.venv/lib/python3.13/site-packages/diffusers/modular_pipelines/modular_pipeline.py", line 1863, in from_pretrained
    pipeline = pipeline_class(
        blocks=blocks,
    ...<5 lines>...
        **kwargs,
    )
  File "/home/unpriv/projects/KeyWest3_ImageGeneration/backend/.venv/lib/python3.13/site-packages/diffusers/modular_pipelines/modular_pipeline.py", line 1686, in __init__
    if blocks_class is not None:
       ^^^^^^^^^^^^
UnboundLocalError: cannot access local variable 'blocks_class' where it is not associated with a value

My current libraries:

[project]
name = "backend"
version = "0.1.0"
description = "Add your description here"
readme = "README.md"
requires-python = ">=3.13"
dependencies = [
    "accelerate>=1.12.0",
    "diffusers>=0.37.0",
    "fastapi[standard]>=0.135.1",
    "huggingface-hub>=1.5.0",
    "nvidia-ml-py>=13.590.48",
    "nvidia-ml-py3>=7.352.0",
    "peft>=0.18.1",
    "torch>=2.10.0",
    "transformers>=5.3.0",
]

[[tool.uv.index]]
name = "pytorch-cu130"
url = "https://download.pytorch.org/whl/cu130"
explicit = true

[tool.uv]
required-environments = [
    "sys_platform == 'linux' and platform_machine == 'aarch64'",
]

[tool.uv.sources]
torch = [
  { index = "pytorch-cu130", marker = "sys_platform == 'linux'" },
]
torchvision = [
  { index = "pytorch-cu130", marker = "sys_platform == 'linux'" },
]
torchaudio= [
  { index = "pytorch-cu130", marker = "sys_platform == 'linux'" },
]

If anyone know something about how to fix this, could you please help?