Currently only Flux.1 [dev], but other Flux models could be AnyFlow distilled into an n-step model.
Bagheera PRO
bghira
AI & ML interests
None yet
Recent Activity
posted an update about 14 hours ago
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!
- https://huggingface.co/datasets/webshart/terminusresearch-photo-anatomy
- https://huggingface.co/datasets/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! updated a dataset about 18 hours ago
webshart/terminusresearch-photo-anatomy updated a dataset 1 day ago
webshart/terminusresearch-photo-aestheticsOrganizations
v-prediction SDXL clone with zero-terminal SNR noise schedule
-
terminusresearch/terminus-xl-gamma-v2-1
Text-to-Image • 3B • Updated • 2 -
terminusresearch/terminus-xl-otaku-v1
Text-to-Image • 3B • Updated • 6 -
terminusresearch/terminus-xl-gamma-training
Text-to-Image • 3B • Updated • 4 -
terminusresearch/terminus-xl-gamma-v2
Text-to-Image • 3B • Updated • 6
Currently only Flux.1 [dev], but other Flux models could be AnyFlow distilled into an n-step model.
Demonstrating SimpleTuner's AnyFlow support by distilling Anima v1.0 using e621 dataset. Recommended weights for inference are dmd-v3 or dmd-v5.
v-prediction SDXL clone with zero-terminal SNR noise schedule
-
terminusresearch/terminus-xl-gamma-v2-1
Text-to-Image • 3B • Updated • 2 -
terminusresearch/terminus-xl-otaku-v1
Text-to-Image • 3B • Updated • 6 -
terminusresearch/terminus-xl-gamma-training
Text-to-Image • 3B • Updated • 4 -
terminusresearch/terminus-xl-gamma-v2
Text-to-Image • 3B • Updated • 6
SD 2.x models with zero terminal SNR noise schedule.