CivArchive
    Hunyuan Image2Video - Upscaling & Frame Interpolation workflow - Fixed I2V Model
    NSFW

    I've created this Hunyuan Image2Video workflow based on Kijai's workflow and added an easy to use interface along with upscaling and frame interpolation.

    Key Features:

    • 1st pass - generating vanilla video

    • 2nd pass upscaling using user selected upscaler and frame interpolation to 48FPS


    This workflow comes pre loaded with my Hunyuan SkyReels RunPod template:
    https://civarchive.com/articles/12253/runpod-template-hunyuan-image2video-with-workflows-included

    Get the new Hunyuan I2V model from Kijai here:

    https://huggingface.co/Kijai/HunyuanVideo_comfy/resolve/main/hunyuan_video_I2V_fp8_e4m3fn.safetensors

    Description

    • Using the new fixed I2V model (Update ComfyUI to the latest version!)

    • Added nodes to remove the first 6 frames of the video as they are junk frames that hurt the natural flow of the video

    FAQ

    Comments (5)

    shatteredApr 1, 2025· 2 reactions
    CivitAI

    The "TeaCacheHunyuanVideoSampler" node always says it is missing/uninstalled even after cloning https://github.com/facok/ComfyUI-TeaCacheHunyuanVideo to the custom nodes folder.

    grande_cojonesMay 17, 2025

    I have the same problem, how to fix this? Updating is not enough

    dskt100Aug 14, 2025

    same, any fix?

    seductivelyai695Apr 18, 2025· 1 reaction
    CivitAI

    Can you put out a version with GGUF... this workflow is slow as molasses because of the huge model.

    gambikules858May 18, 2025

    lol just replace model loader by gguf loader

    Workflows
    Hunyuan Video

    Details

    Downloads
    1,957
    Platform
    CivitAI
    Platform Status
    Available
    Created
    3/9/2025
    Updated
    5/11/2026
    Deleted
    -

    Files

    hunyuanImage2video_fixedI2VModel.zip

    Mirrors