diffusers

diffusers copied to clipboard

Implementation error of v_prediction in eulara and eular

3

I came across a potential inconsistency in the implementation of v_prediction within the Euler scheduler when examining the source code. Specifically, in the computation of pred_original_sample, the formula is given...

yelanyelan

Remove Redundant Arguments Into the doc-string.

2

I’m pleased to announce that I have resolved issue #6634. For a deeper understanding of the solution, you may refer to the issue thread. ## Before submitting - [x] This...

hisushanta

[Tests] fast tests single file checkpoints

6

Even though we support loading single file checkpoints via `from_single_file()`, we only run SLOW tests for them. It's better if we had a fast testing suite for them too. @DN6...

sayakpaul

DDIM produces incorrect samples with SDXL (epsilon or v-prediction)

37

### Describe the bug When generating images with SDXL and DDIM, there is some residual noise in the outputs. This leads to a "smudgy" look, and in cases where fewer...

bghira

RuntimeWarning: invalid value encountered in cast images = (images * 255).round().astype("uint8") output black image

13

### Describe the bug When running the stable-diffusion-2-1 I get a runtime warning "RuntimeWarning: invalid value encountered in cast images = (images * 255).round().astype("uint8")" and the image output is black....

pavankay

fixed deprecation error for euler_discrete scheduler steps offset

1

# What does this PR do? In accordance to the deprecation message: deprecate("steps_offset!=1", "1.0.0", deprecation_message, standard_warn=False) is outdated. "`steps_offset` should be set to 1 instead of 0. Please make sure...

mariopenglee

Regularize Latent input for SD and SDXL img2img

2

I am currently trying to implement seed interpolation in SDNext. This can be done smoothly for SD and SDXL pipelines but not for img2img Currently latents can be passed to...

AI-Casanova

Adding VQGAN Training script

35

# What does this PR do? This is a vqgan training script ported from [taming-transformers](https://github.com/CompVis/taming-transformers) and from lucidrian's muse-maskgit repo [here](https://github.com/lucidrains/muse-maskgit-pytorch) and open-muse. I'm planning to test this on the...

isamu-isozaki

Update train_dreambooth_lora_sd15_advanced.py

10

# What does this PR do? Part of #6891. Notebook - [here](https://huggingface.co/Bhavay-2001/test-model-card-template-Update-train_dreambooth_lora_sd15_advanced) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss...

Bhavay-2001

Being able to input noisy init latents to StableDiffusionPipeline

1

At the moment, two seeds are completely orthogonal to another, i.e. seed=1 and seed=2 have nothing to do with another and are as different as seed=1 and seed=12891371. In Automatic1111,...

nicollegah