Comfy-Org / Comfy-Org/ComfyUI

Microsoft Lens - Turbo, Base, Regular - Image model

Open
#14,048 3 comments 8 reactions 0 assignees View on GitHub
Feature
Dominant language
Python
Stars
133k
Forks
15.7k
Avg merge
1d 7h
Merged PRs (30d)
158

Description

### Feature Idea

Looks pretty good, with GPT-OSS encoder and FLUX.2 VAE
A bit flux/z-image ish, i guess.. but with 4 step turbo model it should be quite interesting to have support for hopefully

https://huggingface.co/microsoft/Lens-Turbo (4 steps, cfg 1)
https://huggingface.co/microsoft/Lens (20 steps, cfg 5)
https://huggingface.co/microsoft/Lens-Base (50 steps, cfg 5)

https://github.com/microsoft/Lens

MIT license

(might already work, but since its GPT-Oss encoder, perhaps it needs something, no idea ;-) And maybe could be repackaged for comfy since the model is across multiple 001, 002 etc files, and fp8 might be lots smaller etc.. )

Image

### Existing Solutions

_No response_

### Other

_No response_

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.