Create & Edit Images Instantly with Grok Imagine

Try Grok Imagine
Skip to main content
 - Release_0.7.7.0.BakedVAE thumbnail

- Release 0.7.7.0.BakedVAE

by ModelsLab
release0770bakedvae
Text to Image Community ModelFree for Premium UsersLLMs.txt

v7.7.0 Release Notes

This update I have added some detail fine tuning. You should see more details in each scene, giving it a more "lived in" feeling for realistic imagery. NV still targets photorealistic portraits and responds really well to photography keywords.

A word of note on sizzle - this model operates best in the 3.5 to 5 CFG range. While you can generate images at 7.5 CFG (the defaults for both A1111 and Comfy for some dumb reason), they're gonna look fried and overbaked and sizzled 🥓 with crushed colors and blown out whites. Lower that CFG down to 5 if you want your colors to pop, or to 3.5 if you want nice neutral color temps that you can toy with to your liking in post.

Changelog 10/27/23

  • added new LoRA SCG-Detailer-V2 (internal only detailer LoRA)

Known Issues

  • Hands

  • Male Genitalia

  • eyes and faces at distance are still iffy. it's getting better, but this is a WIP.

API PlaygroundAPI Documentation