CivArchive
    Wan2.2 - continuous generation (SVI2 Pro | GGUF | 3/2 phase | upscale/interpolate) w/ subgraphs & bus - v0.9
    NSFW

    WARNING: Hey, I've lately moved towards LTX2.3 but I will publish a fix to workflow issues mentioned in comments once I have enough free time.

    I've officially switched to LTX due to slowmo issues with lightx2v loras. I might share a workflow but that model is already capable of 30s on 720p on a 4070ti so I'm not so motivated to do so. This one would still work if you found the missing packages. Thanks everyone for their support.


    It finally happened!
    Now there's a way for smoother continuous videos thanks to SVI team and Kijai.


    We are at v1.0!

    I've updated the workflow to add a few more features;

    • Video extend option by loading an initial video then converting it to latent that goes into first I2V (WIP)

    • Option to switch between 3 and 2 ksampler phases by setting the initial step

    • Option to set cfg > 1 if you wanted to disable lightx2v

    • Images are saved partially in loseless format (use something like VLC to view them) and only loaded again on final merge, if something goes wrong you can merge those files to get a flowing video.

    • Implemented a bus system to reduce connections. Report if you have any issues but things should work as long as you have the right models and loras selected.

    • You can set and fix the seed for each part

    • There are options to upscale and interpolate before final save

    • Final save happens on main graph so you can preview your output

    Slow motion issue probably persists. Couldnt find a consistent solution since when speed up using a third party tool every part becomes faster since they take previous latents as input until everything breaks.

    Weak points of most SVI workflows right now is that it references first image in all parts so you might have background warping/chaning shape/textures on switches if the background has changed a lot.

    I'll only be updating the workflow if kijai updates the node (there are two merge requests about end frame and better consistency(?)) and/or something breaks. So we can call this a semi final :)

    Comfyui compatible SVI lora's;

    https://huggingface.co/Kijai/WanVideo_comfy/blob/main/LoRAs/Stable-Video-Infinity/v2.0/SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora_rank_128_fp16.safetensors

    https://huggingface.co/Kijai/WanVideo_comfy/blob/main/LoRAs/Stable-Video-Infinity/v2.0/SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16.safetensors

    LightX2V lora's I'm using;

    https://huggingface.co/Kijai/WanVideo_comfy/blob/main/LoRAs/Wan22_Lightx2v/Wan_2_2_I2V_A14B_HIGH_lightx2v_MoE_distill_lora_rank_64_bf16.safetensors

    https://huggingface.co/Kijai/WanVideo_comfy/blob/main/LoRAs/Wan22-Lightning/old/Wan2.2-Lightning_I2V-A14B-4steps-lora_LOW_fp16.safetensors

    FP32 vae:

    https://huggingface.co/calcuis/wan-gguf/blob/ff59c62b6a008bc99677228596e096130066b234/wan_2.1_vae_fp32.safetensors

    Ultra Flux VAE for sharper !"Z Image"! outputs:

    https://huggingface.co/Owen777/UltraFlux-v1/blob/main/vae/diffusion_pytorch_model.safetensors

    GGUF still seems to be performing better than fp8 scaled in my experience.

    Just share your outputs with us folks as well :)


    v0.9

    Left sampling on (1 + 3 + 3) steps with 4 parts (19s~). Takes around 10mins on my 4070ti with sage + torch compile. Feel free to extend it further if you need.

    Everything is GGUF. Patch sage attention and torch compile are disabled by default but you are welcome to enable them back since they speed things up a lot if you have the environment set up.

    You can set part specific or common lora's thanks to rgthree power lora node.

    Happy generations! \('-')

    Description

    • added svi support

    FAQ

    Comments (37)

    nikolatesla20145Dec 30, 2025
    CivitAI

    everything is still too much slow motion . WAN 2.2 with Speed up lora slow motion problem sucks

    crombobularDec 30, 2025

    yeah, same. the slowmo kills the entire point of using this.

    iLegoLoon
    Author
    Dec 30, 2025

    My lightx2v loras are kinda outdated, I'll check if I can find the latest compatible ones.

    DomDomTomTomDec 30, 2025· 2 reactions

    Try and use the Seko loras. They're the ones giving me the best results.

    MisticRain69Dec 30, 2025

    Don't use the old lightx2v loras or the wan 2.1 lightx2v/lightening loras. Use the 1022 wan 2.2 low noise lora and the 1030 lightx2v high lora with a total of 6 steps it should help alot.

    hellosirDec 31, 2025

    @MisticRain69 Which version exactly do you mean? 1022 is a Lora, while 1030 is a model.

    Edit: Nevermind. Civit and Hugging have different versions.

    strong134Dec 31, 2025

    @MisticRain69 

    I tried with your recommended loras and it didn't work, same slow video.

    ArtDesignAwesomeJan 1, 2026

    We need a painter node involved...

    Ragamuffin20Jan 2, 2026

    put it through frame interpolation and increase the output frames to like 38 or so. youl have to play with it.

    MoreColorsDec 30, 2025· 1 reaction
    CivitAI

    the image resize node is set to stretch, you need to make it crop the image

    other than that is actually working!

    iLegoLoon
    Author
    Dec 30, 2025· 1 reaction

    Will do thanks, I did not have any input images to test that :(

    Unscathed7928Dec 30, 2025· 2 reactions
    CivitAI

    works beautifully! completely seamless video! although im using the latest lightx2 loras and the triple ksampler node

    iLegoLoon
    Author
    Dec 30, 2025

    triple sampling issue I mentioned earlier could be a false alarm, custom lora's affect the quality a lot. will have to do more tests on the vanilla workflow.

    tcla75542Dec 30, 2025
    CivitAI

    So I ran the workflow without changing anything because chatgpt was saying that the error I was getting was because I must have done something and messed up the wiring but I still get a load of errors like the one below. Did anyone else have this issue?

    Prompt outputs failed validation: CLIPTextEncode: - Return type mismatch between linked nodes: clip, received_type(MODEL) mismatch input_type(CLIP)

    iLegoLoon
    Author
    Dec 30, 2025

    It seems you somehow stuck a model into the clip encode instead of clip. either you've picked the wrong thing or its a graph issue. Make sure to upload your comfyui

    m4rbleyeDec 30, 2025
    CivitAI

    Cannot execute because a node is missing the class_type property.: Node ID '#82:41'

    iLegoLoon
    Author
    Dec 31, 2025· 2 reactions

    Thats WanImageToVideoSVIPro node from kjnodes. Some people reported deleting kjnodes and reinstalling it helped. Might as well reimport workflow after doing that.

    gamumuchoDec 31, 2025· 2 reactions

    Switch the node nightly.

    strong134Dec 31, 2025
    CivitAI


    Thousand thanks for this!

    The only things:

    - The ZIT image creates a back view image of the soldier, but the video shows the soldier from front. Is it suppose to be like that?

    - Every 5 seconds there is a change of perspective in the video, and I don't know why.

    I'm using the default prompts that comes with the workflow.

    iLegoLoon
    Author
    Dec 31, 2025

    Was this one because of the T2V models used by accident?

    strong134Dec 31, 2025· 1 reaction

    You're right!

    @iLegoLoon 

    That's the mistake I made. It's working full wan2.2 with my 4090. And no slowmo. Thanks!

    aeron855Dec 31, 2025
    CivitAI

    What's the benefit of using two different High samplers per section?

    iLegoLoon
    Author
    Dec 31, 2025

    Initial sampling has no lightx2v lora applied and cfg > 1, it gives an initial movement to the video to avoid slowmo and get higher motion out of lightx2v lora applied cfg == 1 samplings. I'll be stepping it up to 2 steps when I reupload the workflow.

    bnzarev821Dec 31, 2025
    CivitAI

    Perfect transitions between the 5s parts and no visible degradation after 2 min video, so i'm pretty happy about the smooth result. But It seems to ignore the prompts after the first part, so the whole generation is like on autopilot (you get some unexpected and interesting results, sometimes even better than the initial plan).

    DisarmedPumpkinJan 1, 2026

    Yep, I'm seeing similar things. It works for the first prompt, but after that it starts doing its own thing and very sensitive to the words you put in the prompt (despite not following it anyway). I wonder what causes that, will need to experiment a bit.

    iLegoLoon
    Author
    Jan 1, 2026· 2 reactions

    Its most likely due to way the latent is made and/or lightx2v. The node takes one reference latent from the very first start image on each step and whole latent of the previous generation. I dont know how it uses/mixes them. I'll try clipping the previous latent and see if it reduces the weird things but the fact that it takes motion-latent-count means that it could already be clipping but reference latent somehow could be suppresing the prompts tho its pure speculation.

    eriocaJan 2, 2026· 1 reaction

    u can increase the cfg as each extend goes by. if you have a more drastic movement on an extended section, u can increase the cfg to let that section more adhere to your prompt.

    10551973Jan 2, 2026
    CivitAI

    This is driving me crazy. I made a 19s video yesterday with this workflow, but I try the exact same thing today and it tells me it can't allocate 79GB of VRAM (no kidding!). I've tried everything I can think of.

    iLegoLoon
    Author
    Jan 2, 2026

    Interesting, at what level does it say that? Can you reimport the workflow in case if something broke? Also I just uploaded v1. I'm not sure if its visible becase civit does not seem to be tagging the images. Can you try that and see if it works?

    10551973Jan 2, 2026

    @iLegoLoon Its the first KSamplerAdvanced. "Tried to allocate 79.96 GiB. GPU 0 has a total capacity of 15.92 GiB of which 5.15 GiB is free." I'll get 1.0 and give it a whirl. I've downloaded the last version a few times to make sure I was using the right file and such.

    10551973Jan 2, 2026

    @iLegoLoon 1.0 doing the same thing: `Tried to allocate 62.83 GiB`

    iLegoLoon
    Author
    Jan 2, 2026

    Can you share the full log? What models are you using? Can it be related to your resolution or video length settings?

    10551973Jan 2, 2026

    @iLegoLoon I checked the specs on the mp4 I managed to make yesterday, the resolution was same as I'm trying today, but the frame count on that file, divided by 4, means I must have lowered the length from 81 to 77 (whether on purpose or a fortuitious fat finger I can't recall). Doing so now (with 1.0) seems like it's chewing through the stages successfully, whereas it used to fail nearly immediately after getting to I2V-First. I'm guessing the fact that I'm using a 16G ROCm card means the overhead is just enough that it doesn't work with your defaults. Go figure. Maybe a note you can make for all us losers with AMD cards.

    iLegoLoon
    Author
    Jan 2, 2026· 1 reaction

    Last time I used an AMD gpu was 15 years ago :) You can also slightly lower the resolution and use simple resize upscale at the end. It wouldnt change much if you dont want to lose video length.

    10551973Jan 3, 2026· 1 reaction

    @iLegoLoon the difference of 4 frames per stage isn't much. I'll just add more stages when I need further video length.

    iLegoLoon
    Author
    Jan 3, 2026

    Thats alright too, if it fails the merge you can merge part files put in temp folder manually using something like shotcut.

    Psi_CloneJan 2, 2026· 4 reactions
    CivitAI

    i tried updating and installing all the missing nodes, but still one of my nodes is missing -

    WanImageToVideoSVIProin subgraph 'I2V-First'

    I don't know which pack it is, but I have installed KJ nodes as it says in the properties panel of the missing node.

    edit - i reinstalled and it still is missing!

    edit 2 - deleted from the custom nodes folder, then git pulled it manually and it worked!

    Workflows
    Wan Video 2.2 I2V-A14B

    Details

    Downloads
    2,658
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/29/2025
    Updated
    6/20/2026
    Deleted
    -