gguf quantized version of t5xxl encoder with mochi (test pack revised)

setup (once)

• drag mochi_fp8_e4m3fn.safetensors (10GB) to > ./ComfyUI/models/diffusion_models
• drag t5xxl_fp16-q4_0.gguf (2.9GB) to > ./ComfyUI/models/text_encoders
• drag mochi_vae_fp8_e4m3fn.safetensors (460MB) 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 (with gguf encoder)
• example workflow (safetensors)

review

• revised workflow to bypass oom issue and around 50% faster with the new fp8_e4m3fn file
• t5xxl gguf works fine as text encoder
• model gguf file might not work; if so, please wait for the code update

reference

• base model from genmo
• comfyui from comfyanonymous
• comfyui-gguf city96
• gguf-comfy pack
• gguf-node (pypi|repo|pack)

prompt test#

prompt: "a fox moving quickly in a beautiful winter scenery nature trees sunset tracking camera"

Prompt

a fox moving quickly in a beautiful winter scenery nature trees sunset tracking camera

Prompt

same prompt as 1st one <metadata inside>

Prompt

same prompt as 1st one; but with new workflow to bypass oom <metadata inside>