SimpleTuner

community

https://github.com/bghira/simpletuner

bghira

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

bghira new activity 22 days ago

SimpleTuner/open-rvq-encoder-minimax-music3:How to help?

bghira updated a model 26 days ago

SimpleTuner/open-rvq-encoder-minimax-music3

bghira new activity 29 days ago

SimpleTuner/open-rvq-encoder-minimax-music3-41m-v1:rvq-encoder-v3-hiddens-best.pt

View all activity

bghira

posted an update 11 minutes ago

Post

Generated ~44 million Cosmos Reasoning captions for CC12M, now available here: webshart/cc12m-structured-captions

- webshart format, indexed with aspect bucketing metadata
- four captions per sample
- simple VLM output
- verbose caption
- a concise caption produced by passing the verbose caption through the model again to remove speculation and flowery language
- an ideogram4 style JSON schema

this used 8x H100 over about 6 days.

bghira

posted an update 8 days ago

Post

2681

I've been gradually recaptioning aged text-to-image datasets with better vision models! These datasets are also repackaged into the more modern webshart format (https://github.com/bghira/webshart) which includes built-in aspect bucketing and caption delivery.

The first two datasets are ready for use!

- webshart/terminusresearch-photo-anatomy
- webshart/terminusresearch-photo-aesthetics

"anatomy" is a bunch of human-centric images containing people holding or otherwise interacting with objects or positioned in complex ways.

"aesthetics" is a collection of visually striking images - high contrast, diverse colouration, and cinematic framing (among other factors).

These two datasets from 2023 were recaptioned with GLM 5.3 Flash via Ollama Cloud and Zhipu AI APIs, with a smaller portion run over 4x H100 with GLM 5.3 Flash in W4A16 precision - these outputs were checked by hand for quality, and the 4bit run was continued at a batch size of 64.

What datasets would you like to see recaptioned next? A better CC12M is on its way!