TowstyandCursor 608f7d8d47 Fix Qwen 2.1 GGUF load: promote Q8 norms to F32 and wire TextEncode latent.
abenzerps Q8_0 ships 1D RMSNorms as packed Q8 (136 vs 128), which breaks
Comfy rms_rope; tagger now dequantizes small tensors and the graph uses
TextEncodeQwenImage21's 64-ch latent plus AuraFlow shift.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-20 16:58:00 -05:00
S
Description
Headless MiniMax H3 image-to-video ComfyUI relay
5.2 MiB
Languages
Vue 41.2%
TypeScript 40.9%
JavaScript 13.1%
PowerShell 1.7%
Python 1.7%
Other 1.3%