Meet the child of Project Chimera and Krea 2 Center.
🧠 Brain: Project Chimera (txtfusion layers)
💪 Body: Based on Krea 2 Center's DiT backbone, with additional refinements.
Chimera provides the model's prompt understanding and interpretation, while the image generation backbone builds upon Krea 2 Center. The result is a model that inherits traits from both parents while developing its own personality.
⚠️ Requirements
Please make sure you're using ComfyUI v0.31.0 or newer. Older builds may not include the required W4A8 support.
Low-VRAM users: I also made a W4A8 quantized Qwen 3 VL 4B text encoder, only 2.86 GB. You can find it here: https://civarchive.com/models/2843533/qwen-3-vl-4b-w4a8?modelVersionId=3210230
Description
main goal was to reduce / tame specular highlights
FAQ
Comments (3)
w4a8 is useless, its extremely slow.
Lots of testing - w4a8 is worse than int8 (less quality and slower) on low VRAM (8GB for me, but by math, anything under 12GB). While the quality gap isn't huge, the generation times can be 20-80% higher.
Love both Chimera and Center - if you do an int8, I would be happy to give it a thorough try.
yeah I think I was just need to hours as I always do learned int8 with adaround ;)