Hugging Face's logo

DmitryDB
/
LTX-2.5-ComfyUI-Quants

Text-to-Video
comfyui
ltx-2.5
quantization
int8
convrot
nvfp4
image-to-video
audio-video
Model card Files
xet
 Community
LTX-2.5-ComfyUI-Quants / MODIFICATIONS.md
DmitryDB's picture
DmitryDB
Publish two searched LTX-2.5 transformer profiles
4487acf verified
preview code
|
Raw
History Blame Contribute Delete
882 Bytes

Modification notice

The files in this repository are quantized derivatives of the official Lightricks LTX-2.5 weights at revision 28dac7acdc1f78a70e98687db261a949754f8941.

Changes made by DmitryDB / DDB:

  • rebuilt Dev and Distilled into two transformer profiles with exact-source DDB searched scaling;
  • published the transformer profiles as int8-convrot and nvfp4;
  • converted the Gemma-4 LTX text encoder to int8, int8_lean_convrot, and nvfp4 profiles;
  • converted the rank-450 Distilled LoRA to three DDB descriptor-based profiles;
  • retained selected sensitive tensors in BF16 according to deterministic architecture-aware policies generated from the BF16 source inventory;
  • added reproducibility recipes, layer policies, integrity hashes, and analysis summaries.

No claim is made that Lightricks authored, approved, or endorsed these modified weights.