metadata

license: apache-2.0
language:
  - en
base_model:
  - genmo/mochi-1-preview
pipeline_tag: text-to-video
tags:
  - mochi
  - t5
  - gguf-comfy
  - gguf-node
widget:
  - text: >-
      a fox moving quickly in a beautiful winter scenery nature trees sunset
      tracking camera
    output:
      url: samples\ComfyUI_00001_.webp
  - text: same prompt as 1st one <metadata inside>
    output:
      url: samples\ComfyUI_00002_.webp
  - text: >-
      same prompt as 1st one; but with new workflow to bypass oom <metadata
      inside>
    output:
      url: samples\ComfyUI_00003_.webp

gguf quantized version of mochi (test pack for gguf-node)

setup (once)

drag mochi-q3_k_m.gguf [4.31GB] 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 works fine as text encoder; more quantized versions of t5xxl can be found here
gguf with pig architecture is working right away; welcome to test

reference

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

prompt test#

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>