diffusers

diffusers copied to clipboard

AttributeError: module diffusers has no attribute DepthNormalEstimationPipeline

3

### Describe the bug Hi, I'm trying to use the [GeoWizzard](https://huggingface.co/lemonaddie/Geowizard) model from the Huggingface Page, I just copied the codes from 'Use in Diffusers' as described on the webpage,...

csyhping

Check shape and remove deprecated APIs in scheduling_ddpm_flax.py

1

`model_output.shape` may only have rank 1. There are warnings related to use of random keys. ``` tests/schedulers/test_scheduler_flax.py: 13 warnings /Users/phillypham/diffusers/src/diffusers/schedulers/scheduling_ddpm_flax.py:268: FutureWarning: normal accepts a single key, but was given a...

ppham27

Something went wrong

1

I'm having an issue in UNet training cell. After trying all types of parameters facing the same something went wrong . i'm using 6 images of dogs of 512*512 resolution....

Sadia7ama

# What does this PR do? Update correct InstantStyle usage in IP-Adapter documentation, as mentioned in #7668 ## Before submitting - [x] This PR fixes a typo or improves the...

JY-Joy

# What does this PR do? Reduces the model sizes in the aMUSEd fast tests. Tagging Issue: https://github.com/huggingface/diffusers/issues/7677 CC: @sayakpaul for visibility.

ariG23498

# What does this PR do? Reduces the model sizes in the DDIM fast tests. Tagging Issue: https://github.com/huggingface/diffusers/issues/7677 CC: @sayakpaul for visibility.

ariG23498

OLSS is the most advanced sampler. Can you consider adding it to the scheduler library of diffusers (https://github.com/alibaba/EasyNLP/tree/master/diffusion/olss_scheduler)

ZihaoW123

set mixed_precision="fp16",but the model is not fp16

5

### Describe the bug I trained the control net of SDXL using the mixed prediction="fp16" parameter, but the trained model did not have the suffix. fp16. safetensors. But it's a...

starinskycc

A strange time cost in denoising loop

5

### Describe the bug I found a stange time cost when I inference StableVideoDiffusionPipeline with GPU. On 3090, the UNet only costs 1.6s, however, a denoising loop costs 3.3s. It...

FEIFEIEIAr

# What does this PR do? Reduces the model sizes in the DDPM fast tests. Tagging Issue: https://github.com/huggingface/diffusers/issues/7677 CC: @sayakpaul for visibility.

ariG23498