metadata

license: apache-2.0
language:
  - en
base_model:
  - Comfy-Org/mochi_preview_repackaged
pipeline_tag: text-to-video
tags:
  - gguf-node
widget:
  - text: >-
      a pinky pig moving quickly in a beautiful winter scenery nature trees
      sunset tracking camera
    output:
      url: samples\ComfyUI_00001_.webp
  - text: >-
      a pinky pig moving quickly in a beautiful winter scenery nature trees
      sunset tracking camera
    output:
      url: samples\ComfyUI_00002_.webp
  - text: >-
      a pinky pig moving quickly in a beautiful winter scenery nature trees
      sunset tracking camera
    output:
      url: samples\ComfyUI_00003_.webp

gguf quantized version of mochi (incl. gguf encoder and gguf vae)🐷🐷🐷

drag mochi to > ./ComfyUI/models/diffusion_models
drag t5xxl to > ./ComfyUI/models/text_encoders
drag vae to > ./ComfyUI/models/vae
drag demo video (below) to > your browser for workflow

Prompt
a pinky pig moving quickly in a beautiful winter scenery nature trees sunset tracking camera

review

new tensor fixed version; load faster with full set gguf (model + encoder + decoder)
upgraded encoder; from fp16/fp8 to fp32; but not affecting the file size and memory consumption; more compatible to old machine
new fp32 gguf vae decoder; similar size to fp16 safetensors; better quality; less ram requirement
q2 works but not usable; you could get q8 [here] pig architecture

reference

base model from genmo
comfyui from comfyanonymous
pig architecture from connector
gguf-node (pypi|repo|pack)