Open jeanhadrien opened 1 year ago
I also want dreambooth with 8 Gb VRAM... Probably worth duplicating the Feature Request here: Dreambooth Extension for Stable-Diffusion-WebUI
Integration with Colossal-AI would be amazing. The speed and VRAM improvements seem to be well worthwhile.
Colossal-AI: A Unified Deep Learning System for Big Model Era
Probably worth duplicating the Feature Request here: Dreambooth Extension for Stable-Diffusion-WebUI
Done:
Also, here are a few other alternative speed/efficiency/etc increase potential issues i'm aware of, each using different techniques/etc:
It looks like the dev team of ColossalAI is looking to work directly with huggingface diffusers to simplify integrations in this issue:
This is very cool @binmakeswell ! Would be very happy to integrate diffusers in colossalAI examples!
Originally posted by @patil-suraj in https://github.com/huggingface/diffusers/issues/1212#issuecomment-1310167948
Thanks for your enthusiastic response and we look forward to working together!
How do you expect it to be carried out? Take our collaboration with Lightning for example, we communicated in slack for details, provided documentation and eventually did a joint release.
Originally posted by @binmakeswell in https://github.com/huggingface/diffusers/issues/1212#issuecomment-1311220560
And there seems to be at least some initial/cursory interest on the issue I opened on the ColossalAI repo RE: integrating with dreambooth:
Hi, thanks for reaching out! I think it’s pretty awesome. Can I check it with our team and get back to you ASAP?
Originally posted by @Sze-qq in https://github.com/hpcaitech/ColossalAI/issues/1935#issuecomment-1313053594
So hopefully things rapidly move towards the 'easier to integrate'/'better documentation' direction of things!
Originally posted by @0xdevalias in https://github.com/ShivamShrirao/diffusers/issues/129#issuecomment-1313059637
any progress?
Sorry for the late reply. The Colossal-AI team is busy with open source ChatGPT recently and received a lot of cooperation interest.
We are expected to have manpower to assist in this work in March. We also look forward to and welcome the participation of the open source community. Thanks.
Is there an existing issue for this?
What would your feature do ?
Integrate ColossalAI improvements : https://github.com/hpcaitech/ColossalAI/tree/main/examples/images/diffusion
Proposed workflow
User is able to toggle improvements by colossal AI
Additional information
No response