diffusers

diffusers copied to clipboard

training fails with torch.float16 dtype - weights are deleted in train loop

3

### Describe the bug i'm using the "textual inversion" training notebooks/scripts. could never get the TPU setup in Flax working, but i blame google for that one - they need...

krahnikblis

Fix typo in pipeline_stable_diffusion.py

2

Fixes a typo in a warning message

scf4

Dream artist issue 1290

2

This is a work-in-progress pr for issue #1290 for dream artist. The dream artist model seems to be the same as the textual inversion model for the most part but...

isamu-isozaki

Accelerate tests fail on 0.6.0 with more than 1 cuda devices

2

### Describe the bug Running the tests from the 0.6.0 tag, the accelerate tests fail with the following stack trace: ``` self = @require_accelerate @unittest.skipIf(torch_device != "cuda", "This test is...

antoche

Potential regression in deterministic outputs

19

### Describe the bug I've started noticing different outputs ~~in the latest version of diffusers~~ starting from diffusers `0.4.0` when compared against `0.3.0`. This is my test code (extracted from...

pcuenca

Improve the precision of our integration tests

6

We currently have a rather low precision when testing our pipeline due to due reasons. 1. - Our reference is an image and not a numpy array. This means that...

patrickvonplaten

use multiple community pipes in a list

5

**Is your feature request related to a problem? Please describe.** I find some very great community pipes, such as CLIP Guided Stable Diffusion and Long Prompt Weighting Stable Diffusion. But...

CrazyBoyM

`StableDiffusionInpaintPipeline` should handle batches

1

I'd like to batch inferences with `StableDiffusionInpaintPipeline`. Most of the code in `pipeline_stable_diffusion_inpaint.py` can do it **except** for `prepare_mask_and_masked_image(image, mask)` which **requires** a `PIL.Image`. **Describe the solution you'd like** A...

vict0rsch

ERROR:torch.distributed.elastic.multiprocessing.api:failed?

12

Hello I've found some problems it`s Before Make Classes, After Finish train If make Classes Image ``` The following values were not passed to `accelerate launch` and had defaults used...

A-Polyana

Hypernetworks

11

**Is your feature request related to a problem? Please describe.** Support for hypernetworks since they seem to yield great results. An example can be seen here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/modules/hypernetworks/hypernetwork.py info: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/2670 **Describe...

dblunk88