GGUF quantized and fp8 scaled versions of LTX Video run it with gguf connector ; simply execute the command below in console/terminal GGUF file(s) available. Select which one to use: 1. ltxv 2b 0.9.8 distilled iq4 nl.gguf 2. ltxv 2b 0.9.8 distilled q6 k.gguf 4. ltxv 2b 0.9.8 distilled q8 0.gguf Enter your choice (1 to 3): opt a gguf file in your current directory to interact with; nothing else note: for the latest update, should be able to adjust number of steps, i.e., for distilled model, use 15 instead of 30; save a lot of loading time run it with gguf node via comfyui drag ltx video 2b v0.9.1 r2 q4 0.gguf (1.09GB) to ./ComfyUI/models/diffusion models drag t5xxl fp16 q4 0.gguf (2.9GB) to ./ComfyUI/models/text encoders drag ltxv vae fp32 f16.gguf (838MB) to ./ComfyUI/models/vae run it straight (no installation needed way) run the .bat file in the main directory (assuming you are using the gguf node pack below) drag the workflow json file (below) to your browser workflow example workflow for gguf (see demo above) example workflow for the original safetensors review q2 k gguf is super fast but not usable; keep it for testing only surprisingly 0.9 fp8 e4m3fn and 0.9 vae fp8 e4m3fn ar…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy