diffusers

diffusers copied to clipboard

Meet error when enabling xformers and doing loss backward

11

### Describe the bug Get error when I enable xformers of UNet and try to do backward: ``` Traceback (most recent call last): File "f:/diffusers-test/vae_expr.py", line 66, in loss.backward() File...

eeyrw

Refactor StableDiffusion example scripts to use Optimum / BetterTransformer optimisations

1

**Describe the solution you'd like** StableDiffusion example scripts are updated to make use of the Optimum / BetterTransformer optimisations. **Describe alternatives you've considered** That the examples can't be integrated, or...

0xdevalias

### Model/Pipeline/Scheduler description Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces abs: https://arxiv.org/abs/2211.07292 github: https://github.com/dome272/Paella t2i model requiring less than 10 steps to sample high-fidelity images ### Open source status...

patrickvonplaten

multiple prediction options in ddpm, ddim

13

starting to work on discussion in #778. Please contribute and leave feedback. This is mostly a placeholder for my work right now as I figure out how to do it....

natolambert

img2img results in noisy image with low num_inference_steps

4

I'm trying to make a video with the `StableDiffusionImg2ImgPipeline` but am encountering some unexpected behavior. I generate the first frame by using the `StableDiffusionPipeline` with relatively many steps (e.g. 100)....

jonasdoevenspeck

Fix bug in half precision for DPMSolverMultistepScheduler

2

The following code fails for the new `DPMSolverMultistepScheduler` when used in half precision due to `torch.quantile()` expecting inputs to be in full precision. This slight patch fixes this bug and...

rtaori

StableDiffusion: Decode latents separately to run larger batches

11

You can use larger batch sizes if you do the VAE decode one image at a time. Now VAE decode runs on the full batch, which limits 8GB GPU batch...

kig

What's the difference between PNDM and plms

2

What's the difference between PNDM and plms，plms for CompVis/stable-diffusion-v1-4-origin

dingjingzhen

DiffusionDet: Diffusion models for object detection

19

### Model/Pipeline/Scheduler description Recent work which leverages diffusion models for object detection task. https://arxiv.org/abs/2211.09788 Add capability to run it through HF diffusers pipeline and if possible also create benchmarks or...

345ishaan

patrickvonplaten