metadata

license: mit
license_name: tencent-hunyuan-community
license_link: LICENSE
datasets:
  - trojblue/test-HunyuanVideo-anime-images
  - calcuis/anime-descriptor
language:
  - en
base_model:
  - tencent/HunyuanVideo
pipeline_tag: text-to-video
tags:
  - hyvid
  - lora
  - gguf-comfy
widget:
  - text: >-
      anime scene of a vibrant carnival with colorful rides, games, and food
      stalls, and a cute anime girl with multicolored hair, holding a melting
      ice-cream, wearing a fluffy white hoodie and blue mini shorts, winking her
      eye, smiling to the camera
    output:
      url: samples\ComfyUI_00002_.webp
  - text: >-
      anime girl with pink twin tails and green eyes, wearing a school uniform,
      holding a stack of books in a bustling library filled with sunlight
      streaming through tall windows
    output:
      url: samples\ComfyUI_00001_.webp
  - text: '* prompt (demo) inside metadata: <drag it to browser> (apply to all)'
    output:
      url: samples\ComfyUI_00006_.webp
  - text: >-
      anime boy with silver hair and blue eyes, wearing a casual hoodie, sitting
      on a park bench, feeding pigeons with a gentle smile
    output:
      url: samples\ComfyUI_00003_.webp
  - text: >-
      anime style anime girl with massive fennec ears and one big fluffy tail,
      she has blonde long hair blue eyes wearing a maid outfit with a long black
      gold leaf pattern dress, walking slowly to the front with sweetie smile,
      holding a fancy black forest cake with candles on top in the kitchen of an
      old dark Victorian mansion lit by candlelight with a bright window to the
      foggy forest
    output:
      url: samples\ComfyUI_00004_.webp
  - text: >-
      anime style anime girl with massive fennec ears and one big fluffy tail,
      she has blonde hair long hair blue eyes wearing a pink sweater and a long
      blue skirt walking in a beautiful outdoor scenery with snow mountains in
      the background
    output:
      url: samples\ComfyUI_00005_.webp

Prompt
anime scene of a vibrant carnival with colorful rides, games, and food stalls, and a cute anime girl with multicolored hair, holding a melting ice-cream, wearing a fluffy white hoodie and blue mini shorts, winking her eye, smiling to the camera

Prompt
anime girl with pink twin tails and green eyes, wearing a school uniform, holding a stack of books in a bustling library filled with sunlight streaming through tall windows

Prompt
* prompt (demo) inside metadata: <drag it to browser> (apply to all)

Prompt
anime boy with silver hair and blue eyes, wearing a casual hoodie, sitting on a park bench, feeding pigeons with a gentle smile

Prompt
anime style anime girl with massive fennec ears and one big fluffy tail, she has blonde long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress, walking slowly to the front with sweetie smile, holding a fancy black forest cake with candles on top in the kitchen of an old dark Victorian mansion lit by candlelight with a bright window to the foggy forest

Prompt
anime style anime girl with massive fennec ears and one big fluffy tail, she has blonde hair long hair blue eyes wearing a pink sweater and a long blue skirt walking in a beautiful outdoor scenery with snow mountains in the background

GGUF quantized and fp8 scaled version of hyvid with lora anime adapter

Setup (once)

drag hyvid_lora_adapter.safetensors [323MB] to > ./ComfyUI/models/loras
drag hunyuan-video-t2v-720p-q4_0.gguf [7.74GB] to > ./ComfyUI/models/diffusion_models
drag clip_l.safetensors [246MB] to > ./ComfyUI/models/text_encoders
drag llava_llama3_fp8_scaled.safetensors [9.09GB] to > ./ComfyUI/models/text_encoders
drag hunyuan_video_vae_bf16.safetensors [493MB] 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-comfy pack below)
drag the demo clip or the workflow json file (below) to > your browser

Workflows

example workflow for gguf (prepare two quantized files to switch while oom occurs)
example workflow for safetensors (fp8 scaled version [13.2GB] is recommended)

References

base model from tencent
fast model from fastvideo
lora adapter from trojblue
comfyui from comfyanonymous
gguf node from city96
gguf-comfy pack

Appendices

get more test prompt from the training dataset
still no ideas? get fresh prompt from our simulator