NVIDIA / NVIDIA/TensorRT

Switch to AutoencoderTiny in Diffusers Examples

Open
#3,783 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

triaged
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

I'm trying to switch to AutoencoderTiny from AutoencoderKL in demo_txt2img_xl with Turbo model. After some attempts to changing models.py it finally works, but images comes with artifacts.

python demo_txt2img_xl.py "Einstein" --version xl-turbo --onnx-dir onnx-sdxl-turbo --engine-dir engine-sdxl-turbo --denoising-steps 1 --scheduler EulerA --guidance-scale 0  --width 512 --height 512

xl_base-Einstein-None-1-6187

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with demo/Diffusion/models.py and demo_txt2img_xl.py, then run the provided xl-turbo command to reproduce the artifacts. Trace the AutoencoderTiny switch in the example and compare its generated output with the shown result. Done means the example uses AutoencoderTiny with the Turbo model and produces images without the reported artifacts.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
42/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.