huggingface / huggingface/diffusers

No Attributte: when i run pixart-alpha with time_step=1, error occured.

Open
#9,106 3 comments 0 reactions 0 assignees View on GitHub
bug stale
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

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.