Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Lumina: RuntimeError: shape '[2, 4, 67, 2, 120, 2]' is invalid for input of size 259200 #10650

Open
nitinmukesh opened this issue Jan 25, 2025 · 1 comment · May be fixed by #10651
Open

Lumina: RuntimeError: shape '[2, 4, 67, 2, 120, 2]' is invalid for input of size 259200 #10650

nitinmukesh opened this issue Jan 25, 2025 · 1 comment · May be fixed by #10651
Labels
bug Something isn't working

Comments

@nitinmukesh
Copy link

nitinmukesh commented Jan 25, 2025 •
edited
Loading

Describe the bug

If I use width=1920 and height=1080, error reported

Documentation says both should be divisible by 8
https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/lumina/pipeline_lumina.py

if height % 8 != 0 or width % 8 != 0:
raise ValueError(f"height and width have to be divisible by 8 but are {height} and {width}.")

The following works, 1024x576 and 1024x2048.

Reproduction

import torch
from diffusers import LuminaText2ImgPipeline

pipe = LuminaText2ImgPipeline.from_pretrained(
	"Alpha-VLLM/Lumina-Next-SFT-diffusers", torch_dtype=torch.bfloat16
)
# Enable memory optimizations.
pipe.enable_model_cpu_offload()
pipe.vae.enable_slicing()
pipe.vae.enable_tiling()
prompt = "Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. Background shows an industrial revolution cityscape with smoky skies and tall, metal structures"
image = pipe(
    prompt=prompt,
    width=1920,
    height=1080
).images[0]

Logs

File "C:\aiOWN\diffuser_webui\lumina.py", line 11, in <module>
    prompt = "Upper body of a young woman in a Victorian-era outfit with brass goggles and leather straps. Background shows an industrial revolution cityscape with smoky skies and tall, metal structures"
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\diffusers\pipelines\lumina\pipeline_lumina.py", line 846, in __call__
    noise_pred = self.transformer(
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\accelerate\hooks.py", line 175, in new_forward
    output = module._old_forward(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\diffusers\models\transformers\lumina_nextdit2d.py", line 310, in forward
    hidden_states, mask, img_size, image_rotary_emb = self.patch_embedder(hidden_states, image_rotary_emb)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1736, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\aiOWN\diffuser_webui\venv\lib\site-packages\diffusers\models\embeddings.py", line 609, in forward
    x = x.view(batch_size, channel, height_tokens, patch_height, width_tokens, patch_width).permute(
RuntimeError: shape '[2, 4, 67, 2, 120, 2]' is invalid for input of size 259200

System Info

- 🤗 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: not installed
- Bitsandbytes version: 0.45.0
- 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>

Who can help?

No response
@nitinmukesh nitinmukesh added the bug Something isn't working label Jan 25, 2025
@victolee0
Copy link

I think the check_inputs function is incorrect. Since the VAE reduces the image size by a factor of 8 and patch_size=2, the height and width must be divisible by 16.

@victolee0 victolee0 linked a pull request Jan 25, 2025 that will close this issue
Open
6 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

fix check_inputs func in LuminaText2ImgPipeline victolee0/diffusers
2 participants
@nitinmukesh @victolee0