huggingface / huggingface/diffusers
No Attributte: when i run pixart-alpha with time_step=1, error occured.
- Dominant language
- Python
- Stars
- 34.5k
- Forks
- 7.3k
- Avg merge
- 3d 3h
- Merged PRs (30d)
- 91
Description
### Describe the bug
File "/home/luor/miniconda3/envs/aigc-inf/lib/python3.9/site-packages/diffusers/pipelines/pixart_alpha/pipeline_pixart_alpha.py", line 942, in __call__
latents = self.scheduler.step(noise_pred, t, latents, **extra_step_kwargs).pred_original_sample
AttributeError: 'SchedulerOutput' object has no attribute 'pred_original_sample
@yiyixuxu @sayakpaul
### Reproduction
pipe = DiffusionPipeline.from_pretrained("raman07/pixart-alpha-256x256", )
h,w = 224,224
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(
prompt,
height=h,
width=w,
num_inference_steps=1).images[0]
### Logs
_No response_
### System Info
pytorch 2.3.0
diffusers 0.29.2
transformers 4.43.3
### Who can help?
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.