CivArchive

    My ComfyUI workflows for using Wan 2.2

    This workflows are used by me to create my art.

    They are optimized for my checkpoints and created of my latest knowledge to enhance the outcome.
    "If this workflow leveled up your day, I'd purr-eciate a like! ๐Ÿ˜ป"


    Versions & Information๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡

    ๐Ÿ‘‰ Please read below and the file descriptions "About this version" for more info's.

    ๐ŸŽฌ๐ŸˆClick me! HowTo + Video

    ๐Ÿ’กSome WAN 2.2 versions use high+low checkpoints, other like S2V use only a single checkpoint - make sure to read the descriptions and use the correct checkpoints.

    โš ๏ธ Do not use the workflows with the "Nodes 2.0 beta" from ComfyUi or it will mess up things.
    ๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡๐Ÿ‘‡


    What you get from the comfy workflows:

    • โ™จ๏ธ Easy controls

    • โœ… As less as possible dependencies

    • ๐Ÿชง Detailed documentation

    • โ›“๏ธ Highly automatic logic

    • โœจ Optimized results

    • ๐ŸŽฌ Fully automated resolution logic

    • ๐Ÿ”– Bookmark-Shortcuts with number keys


    Types of workflows

    FastFidelity C-AiO

    • ๐Ÿ–ผ๏ธ I2V and FLF2V

    • ๐Ÿงฉ Automatic aspectโ€‘ratio calculation and fitting

    • โœจ Multiple Upscalers

      • Torchlanc (very fast, color correct, low VRAM)

      • Upscale with Model (additional detail, high quality)

      • RTX Super Resolution (ultra fast, very accurate)

    • ๐Ÿค Video resolution matching - Fully automatic scaling and resolution calculations

    • ๐Ÿ•  Length automation - Fully automatic calculation of frame count

    • ๐Ÿซฅ Watermark option

    • ๐Ÿงฎ Color match feature

    • ๐Ÿ‘พ MiniMeme feature - Create small gif's

    • ๐ŸŽญ NAG - Negative prompting with CFG1

    • ๐Ÿช„ Interpolation feature

    • ๐ŸŒ€ Perfect loop feature

    • ๐Ÿƒ Last Frame Extraction

    • ๐Ÿ”– Bookmark-Shortcuts - with number keys

    FastFidelity C-SVI

    • ๐Ÿ–ผ๏ธ SVI (SVI 2.0 up to 10 samplers)

    • ๐Ÿงฉ Automatic aspectโ€‘ratio calculation and fitting

    • โœจ Ultraโ€‘fast, colorโ€‘correct upscaling (torchlanc) OR Upscale with Model

    • ๐Ÿค Video resolution matching - Fully automatic scaling and resolution calculations

    • ๐Ÿ•  Length automation - Fully automatic calculation of frame count

    • ๐Ÿซฅ Watermark support

    • ๐Ÿช„ Interpolation feature

    • ๐Ÿ”– Bookmark-Shortcuts - with number keys

    Swarm Basic

    • Absolute basic SwarmUI preset

    • Not recommended over ComfyUI for video generation

    Backend Test

    • If this does not create the example video your ComfyUI backend is broken.

    • If this works, but your other workflow not, the other workflow is broken or missing dependencies


    ๐Ÿฉป Known issues and advice's

    • โš ๏ธ Some workflows may set on webp av1 encoding (VHS node) - If your computer/setup missing drivers use any other like H265 or H264!

    • Install ffmpeg!

    • Update Comfyui and custom_nodes!

    • Update pytorch 2.9+cu128 or higher

    • Make sure to read where files/models should be placed inside the workflow

    • Check if the filepath for model/clip/vae match your system like Linux/Windows

    • The plugin ComfyUI-DD-Translation can break node connection (avoid)


    All older Versions are available inside my GitHub Repo.


    Spacial thanks to @Abyss_Games for a really good idea and help with the "loop"!

    I got some really good ideas from @Gladas workflows!


    YOU are responsible for outputs as always! If you make ToS violating content and I get aware I WILL report this.

    Description

    Version 1.2 (SwarmUI):

    Version optimised for SwarmUI 0.9.7

    Added Lightning Lora settings

    FAQ

    Comments (9)

    jekestarSep 8, 2025ยท 3 reactions
    CivitAI

    Given groups=1, weight of size [5120, 36, 1, 2, 2], expected input[1, 32, 21, 120, 120] to have 36 channels, but got 32 channels instead

    whats the problem.

    darksidewalkerSep 8, 2025ยท 1 reaction

    Maybe your comfy is not up2date?

    TripTrapOct 14, 2025ยท 1 reaction

    same here

    darksidewalkerOct 14, 2025ยท 2 reactions

    Wrong VAE or comfy not up2date.

    TripTrapOct 14, 2025ยท 1 reaction

    @darksidewalkerย yup- out of date comfyui. Works now

    fenrirw56942Sep 11, 2025ยท 2 reactions
    CivitAI

    Why are you using VAE wan2.1 for wan2.2?

    darksidewalkerSep 11, 2025ยท 7 reactions

    Because Wan 2.2 VAE is broken and was never fixed, as much as I know.

    Adaptalab0rSep 28, 2025ยท 3 reactions

    I thought Wan2.2 is for WanT2I2V 5 Billion Parameter model only. I think it was never inteded to work with Wan2.2. But maybe I'm wrong.

    antigaSep 29, 2025ยท 1 reaction

    Even Wan-AI says to use wan2.1 with 14B ^^

    Workflows
    Wan Video 2.2 I2V-A14B

    Looks like we don't have an active mirror for this file right now.

    CivArchive is a community-maintained index โ€” we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.

    Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.

    Details

    Downloads
    710
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    8/29/2025
    Updated
    6/3/2026
    Deleted
    11/6/2025

    Files

    wan22A14BHighLowI2V_swarmui2LoraV12.zip

    Mirrors