Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Pre-emptive Feature anticipation #4

Open
11 tasks
TomLucidor opened this issue Oct 23, 2024 · 11 comments
Open
11 tasks

Pre-emptive Feature anticipation #4

TomLucidor opened this issue Oct 23, 2024 · 11 comments
Labels
Answered Answered the question working working on this issue

Comments

@TomLucidor
Copy link

Probably gonna shortlist some wonky idea, but hey if this tool will be workable anywhere it better be feature-full

@lawrence-cj
Copy link
Collaborator

Nice one. We will work on the function supporting works including the ones you listed above during this whole year. Also we will keep improving the quality of DC-AE and Sana, planning to release like v1.5 in the futher. Trying to make the high-compression tech popular.

@doogyhatts
Copy link

I need to add some features too as I had been using PixArt-Sigma and found some success with it.

  1. Achieve a similar midjourney-style aesthetic quality, currently found in PixArt-Sigma.
  2. Include image datasets that were used for training PixArt-Sigma model.

@lawrence-cj
Copy link
Collaborator

lawrence-cj commented Oct 24, 2024

Definitely, I am willing to integrate these features.

@TomLucidor
Copy link
Author

@doogyhatts please do not have aesthetic locking, since coming from the SDXL derivative side of things, people have really put in effort to make everything aesthetically flexible.

@doogyhatts
Copy link

@doogyhatts please do not have aesthetic locking, since coming from the SDXL derivative side of things, people have really put in effort to make everything aesthetically flexible.

Simply have different base models, including one that does not have any style-specific datasets applied to it.

@TomLucidor
Copy link
Author

TomLucidor commented Oct 30, 2024

@doogyhatts here is the thing tho... if there is a way to create a style embedding for all major implicit styles (looking at the current and future methodology of Pony), then the problem of style bias becomes trivial, and finetuning (or pruning) would be easier. LoRA extractors kind of do this already.

@Deng-Xian-Sheng
Copy link

my boss that me use this model

but no lora train, I no idea finish work.

@Deng-Xian-Sheng
Copy link

help me please.

@TomLucidor
Copy link
Author

TomLucidor commented Dec 6, 2024

@lawrence-cj Advent calendar or bust, bro XD 🕙
but seriously make a timeline of this with conservative estimates would be sweet

@lawrence-cj
Copy link
Collaborator

lawrence-cj commented Dec 6, 2024

I'm not resting. You tell me the priority or do something to help, pls? @TomLucidor

city96/ComfyUI_ExtraModels#84
huggingface/diffusers#9982
huggingface/diffusers#9708
BF16 model fine-tuning
bghira/SimpleTuner#1187

@lawrence-cj
Copy link
Collaborator

LoRA is supported in diffusers
refer to:
https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sana.md
and
Official diffusers docs: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_sana.md

@lawrence-cj lawrence-cj reopened this Dec 18, 2024
@lawrence-cj lawrence-cj added Answered Answered the question working working on this issue labels Dec 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Answered Answered the question working working on this issue
Projects
None yet
Development

No branches or pull requests

4 participants