CivArchive
    MiniMax H3 PDD 8 Step FL2VA - v1.0
    Preview 142554625


    AI-KSK ComfyUI workflow: MiniMax H3 PDD 8 Step FL2VA.

    This workflow is the PDD 8-step first-last-frame route. It uses the PDD 8-step setup node on the MiniMax H3 FL2VA INT8 model with both endpoint frames, then decodes with the MiniMax H3 audio-video decoder into VHS video export.

    Main features:
    - PDD 8-step setup node for the MiniMax H3 FL2VA INT8 model
    - First and last frame input plus text prompt
    - Qwen3-VL 32B MiniMax text encoder with video and audio VAEs
    - 8-step distilled schedule via the PDD setup node
    - MiniMax H3 AV decode to H.264 MP4 with audio

    Suggested workflow:
    Use this route when the shot has fixed start and end frames and you want a distilled-speed render. Keep the two endpoint frames consistent in lighting, scale, and framing.

    RunningHub workflow (try online, no install needed):
    https://www.runninghub.ai/zh-cn/post/2098328697479983105?inviteCode=rh-v1111

    AI-KSK RunningHub workflow hub:
    https://www.runninghub.ai/user-center/1892566146468511746?inviteCode=rh-v1111

    Bilibili tutorial:
    https://www.bilibili.com/video/BV16DYL6FEsh/

    RunningHub registration and AI tools:
    https://www.runninghub.ai/?inviteCode=rh-v1111
    https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111
    https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111
    https://rhtv.runninghub.ai/projects?inviteCode=rh-v1111

    Stable global access:
    https://lelians.com/#/register?code=mFIJ5tZn

    TokenRhythm AI model credits:
    https://tokenrhythm.studio/i/rf_tr_kM6wekDquDDZQD4PUNmgiuHA

    Youyun Cloud GPU:
    https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq
    https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52

    RunPod Cloud GPU:
    https://runpod.io/?ref=sxk5n5m7

    Support AI-KSK:
    https://ko-fi.com/aiksk

    Description



    AI-KSK ComfyUI workflow: MiniMax H3 PDD 8 Step FL2VA.

    This workflow is the PDD 8-step first-last-frame route. It uses the PDD 8-step setup node on the MiniMax H3 FL2VA INT8 model with both endpoint frames, then decodes with the MiniMax H3 audio-video decoder into VHS video export.

    Main features:
    - PDD 8-step setup node for the MiniMax H3 FL2VA INT8 model
    - First and last frame input plus text prompt
    - Qwen3-VL 32B MiniMax text encoder with video and audio VAEs
    - 8-step distilled schedule via the PDD setup node
    - MiniMax H3 AV decode to H.264 MP4 with audio

    Suggested workflow:
    Use this route when the shot has fixed start and end frames and you want a distilled-speed render. Keep the two endpoint frames consistent in lighting, scale, and framing.

    RunningHub workflow (try online, no install needed):
    https://www.runninghub.ai/zh-cn/post/2098328697479983105?inviteCode=rh-v1111

    AI-KSK RunningHub workflow hub:
    https://www.runninghub.ai/user-center/1892566146468511746?inviteCode=rh-v1111

    Bilibili tutorial:
    https://www.bilibili.com/video/BV16DYL6FEsh/

    RunningHub registration and AI tools:
    https://www.runninghub.ai/?inviteCode=rh-v1111
    https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111
    https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111
    https://rhtv.runninghub.ai/projects?inviteCode=rh-v1111

    Stable global access:
    https://lelians.com/#/register?code=mFIJ5tZn

    TokenRhythm AI model credits:
    https://tokenrhythm.studio/i/rf_tr_kM6wekDquDDZQD4PUNmgiuHA

    Youyun Cloud GPU:
    https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq
    https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52

    RunPod Cloud GPU:
    https://runpod.io/?ref=sxk5n5m7

    Support AI-KSK:
    https://ko-fi.com/aiksk
    Workflows
    Other

    Details

    Downloads
    28
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/12/2026
    Updated
    9/13/2026
    Deleted
    -

    Files

    minimaxH3PDD8Step_v10.json

    Mirrors

    CivitAI (1 mirrors)