Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
This repository was archived by the owner on Nov 27, 2024. It is now read-only.

Model WishList #66

saddam213 started this conversation in General
Dec 11, 2023 · 6 comments · 5 replies
Discussion options

As you know I have no idea or way to convert models to ONNX format, I rely solely on the community

There are a few models I need in ONNX format to help in my development efforts, if anyone out there would like to convert some of there for me it would be epic!!!

StableDiffusion

AnimateDiff

ControlNet

Upscalers:

TAESD

LoRA

You must be logged in to vote

Replies: 6 comments 5 replies

Comment options

forserx's page has onnx pix2pix and controlnet =
https://huggingface.co/ForserX

@AshD @ForserX can u guys please help our friend for converting these models?

btw, Stable Video Diffusion img2vid is a very good img to video, maybe easier than animatediff to impelement

You must be logged in to vote
3 replies
Comment options

saddam213 Dec 11, 2023
Maintainer Author

Thanks for that link, thats heaps off the list :)

Comment options

Does this model cover the need for LCM-Lora?
https://huggingface.co/softwareweaver/Latent-Consistency-xl-Olive-Onnx

Comment options

I did video generation as follows: I split the input video into 24 frames per second, processed a packet of frames, after which I baked back the video from the received images via ffmpeg/opencv.

Comment options

For upscalers, I'll say this: there are C++ implementations with vulkan models. They work out less than a second. If you are interested, I can give you links.

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
0 replies
Comment options

I added a SDXL DPO model
https://huggingface.co/softwareweaver/sdxl-dpo-Olive-Onnx

Direct Preference Optimization (DPO) for text-to-image diffusion models is a method to align diffusion models to text human preferences by directly optimizing on human comparison data. https://arxiv.org/abs/2311.12908

In my limited testing, It seems to follow my prompts better.

You must be logged in to vote
2 replies
Comment options

saddam213 Dec 20, 2023
Maintainer Author

Nice, downloading now...

Comment options

Added a new model that combines DPO with LCM. Should have the features of DPO with the speed of LCM.

https://huggingface.co/softwareweaver/SDXL-DPO-LCM-Olive-Onnx

Comment options

saddam213
Jan 12, 2024
Maintainer Author

Anyone had any luck converting Animatediff or StableDiffucionVideo models?

would be awesome to add support for those

You must be logged in to vote
0 replies
Comment options

saddam213
Jan 19, 2024
Maintainer Author

LCM-LoRA-SD - Disty0/LCM_SoteMix

You must be logged in to vote
0 replies
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request help wanted Extra attention is needed

AltStyle によって変換されたページ (->オリジナル) /