CivArchive
    WAN 2.2 IT2V SageAtt 12GB Friendly. - v1.0
    NSFW

    This is a simple WAN2.2 Image to video and text to video workflow that I've pieced together and modified. SageAttention can be disabled but its highly recommended. It vastly improves generation times. This workflow has been my goto. I've added Diffusion models and GGUF models to the I2V and T2V sections. You will need to disable one or the other. To change simply match the model outputs connecting to SageAtt. Credit goes out to @Akalabeth or the original workflow. This person is very talented, I highly recommend giving them a follow.

    Description

    FAQ

    Comments (28)

    atral340478Sep 20, 2025
    CivitAI

    Doesn't work... wanBlockSwap error ("NoneType", object has no attribute "clone") but gguf has installed

    dreadfulpirate
    Author
    Sep 20, 2025

    How much system RAM do you have?

    atral340478Sep 20, 2025

    @dreadfulpirate 12gb gpu + 32 

    dreadfulpirate
    Author
    Sep 20, 2025

    @atral340478 Hello. Are you using the T2V or I2V? Each section has two sets of base models, one set is the diffusion model and the other set is GGUF model. Can you make sure you've disabled/bypassed the unconnected model?

    dominic1336756Sep 20, 2025· 1 reaction
    CivitAI

    Working perfectly. Thank you

    miketheninja446Oct 7, 2025
    CivitAI

    Works great for T2V. But I2V gives me this error "cannot import name 'sageattn_qk_int8_pv_fp16_triton' from 'sageattention'" Tried clean install of comfy, sage, and triton but no luck. And disabling sage via the switch gives me this error "("NoneType", object has no attribute "clone")".

    dreadfulpirate
    Author
    Oct 8, 2025

    Hello. Are you using the T2V or I2V? Each section has two sets of base models, one set is the diffusion model and the other set is GGUF model. Can you make sure you've disabled/bypassed the unconnected model?

    miketheninja446Oct 8, 2025· 1 reaction

    I ended up getting this to work by switching the patch sageattention nodes to auto within the I2V block. Many generations now and its working good. And just to answer the question I was trying to do I2V, I was using GGUF models and had disabled the other model nodes.

    dreadfulpirate
    Author
    Oct 8, 2025

    @miketheninja446 I'm glad you got it working. Thanks for the update.

    durachellOct 12, 2025
    CivitAI

    Enabled i2v
    disabled both Unet Loader GGUF
    Enabled+connected both Diffusion model (wan2.2_ti2v_5B_fp16.safetensors)
    SA enabled

    KSamplerAdvanced

    Expected all tensors to be on the same device, but got weight is on cpu, different from other tensors on cuda:0 (when checking argument in method wrapper_CUDA__native_layer_norm)

    dreadfulpirate
    Author
    Oct 12, 2025

    I ran into this problem before. The only way I resolved this was by closing comfyui and restarting. Let me know if that works or not.

    durachellOct 13, 2025

    @dreadfulpirate got a feeling that I'm using a wrong model? (non gguf). Using gguf output is... broken, output is brown.

    dreadfulpirate
    Author
    Oct 13, 2025

    @durachell I will test it out on my end today.

    dreadfulpirate
    Author
    Oct 16, 2025

    @durachell I have not been able to generate any errors. What are your system specs?

    durachellNov 3, 2025· 1 reaction

    @dreadfulpirate Thanks for the follow ups, I don't think it's specs, but I have 3060 12GB VRAM. I'm new to GGUF and ti2v generation and comfyui. Consider me as a rookie.

    dreadfulpirate
    Author
    Nov 3, 2025

    @durachell Were you able to resolve the issue?

    durachellFeb 2, 2026

    @dreadfulpirate may I know the version of comfyui you use?

    dreadfulpirate
    Author
    Feb 2, 2026

    @durachell Currently, ComfyUI Manager V3.39.2.

    durachellFeb 3, 2026

    @dreadfulpirate Thanks for replying. I mean the base comfyui version, not the custom nodes or other nodes.

    dreadfulpirate
    Author
    Feb 3, 2026

    @durachell No problem, glad to help.. Is this the information you needed?

    ComfyUI 0.11.1

    ComfyUI_frontend v1.37.11

    Discord

    ComfyOrg

    LoRA Manager v0.9.14-stable

    EasyUse v1.3.7

    rgthree-comfy v1.0.2512112053

    ComfyUI-Manager V3.39.2

    System Info

    OS

    win32

    Python Version

    3.12.8 (tags/v3.12.8:2dc476b, Dec 3 2024, 19:30:04) [MSC v.1942 64 bit (AMD64)]

    Embedded Python

    true

    Pytorch Version

    2.9.1+cu130

    Arguments

    ComfyUI\main.py --disable-auto-launch --force-upcast-attention

    RAM Total

    31.94 GB

    RAM Free

    19.32 GB

    durachellFeb 20, 2026· 1 reaction

    @dreadfulpirate ok so, I need to reboot the machine to solve node issues. All good. Thanks.

    ceelogreen855Nov 14, 2025
    CivitAI

    works well but for some reason the generated videos try to end close to the starting image even when I'm not prompting for it. eg. if the starting image is a woman's face and my prompt is: a woman turns around (simplified in this example of course). the video will have her turn around and the video should end but instead she turns back around and shows her face

    dreadfulpirate
    Author
    Nov 14, 2025

    Anyway I can see your results?

    ceelogreen855Nov 15, 2025

    @dreadfulpirate not sure how to upload results but it has to do with the length of the video. at 8 seconds it always resets to close to the starting image. anything above 8 will have the video reset close to the starting image at 8 seconds and then do another second (if set to 9) or 2 (if set to 10) of animation. setting it to 7 seconds avoids the 8 second reset. not sure why it does that at 8 seconds or if there's a workaround

    dreadfulpirate
    Author
    Nov 15, 2025

    @ceelogreen855 I will have to look into it. Personally I've never tried generating 8 seconds of video. Also I am getting ready to post a new workflow. Has many improvements.

    anzzio487Dec 1, 2025
    CivitAI

    I just cant get it to work

    dreadfulpirate
    Author
    Dec 1, 2025

    Whats the problem?

    jadicomanFeb 18, 2026
    CivitAI

    Not found nodes error
    JWIntegerDiv

    JWFloatToInteger

    JWImageResizeByLongerSide

    Workflows
    Wan Video 2.2 TI2V-5B

    Details

    Downloads
    2,192
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/20/2025
    Updated
    4/28/2026
    Deleted
    -

    Files

    wan22IT2VSageatt12GB_v10.zip

    Mirrors

    CivitAI (1 mirrors)