CivArchive
    LTX 2 Workflow ( Text-To-Video & Image-To-Video ) - v1.0

    This is the video that i made for ltx 2 .

    Check it out and want models links and all check out my discord - https://discord.com/channels/1350055016987365436/1457085486056214598/1458455052871143434

    Description

    FAQ

    Comments (51)

    BrownRecluse666Jan 7, 2026· 5 reactions
    CivitAI

    What's your take on LTX 2, Better than Wan 2.2?

    gambikules858Jan 7, 2026· 3 reactions

    15sec+ length, high resolution + speed generation. possible voice from text.

    PrefoJan 8, 2026· 7 reactions

    It's kinda amazing for the reasons already mentioned. That being said - I'm having more issues with prompt adherence with it than I do with Wan 2.2. I'm early into my experimenting with it but if I can address the prompt adherence stuff (and if good Loras are possible) then I will be ditching Wan 2.2. Mostly because of the speed improvement. I don't necessarily find the video quality that much different in FP8. I also really like the audio generation being integrated into a single pass.

    dominic1336756Jan 8, 2026· 2 reactions

    No...

    AiVerse
    Author
    Jan 8, 2026

    I think this has the potential to be better than wan 2.2 . POTENTIAL :D

    LoreweaverJan 8, 2026

    I think it's amazing except for the censorship, which someone will probably fix soon by releasing a NSFW checkpoint. A newer&better model could come out next week though. Which seems to happen faster and faster these days. It feels hard to invest in a model when it often just becomes obsolete after a week.

    skeetfontenot496Jan 8, 2026

    I run out of memory. Any way to make this work on a GPU with 16GB memory and offload to System memory?

    janssenbuttonJan 8, 2026

    @skeetfontenot496 check the other comments claiming that pagefile.sys will do the trick. I don't have doubts it will work. I just didn't try it since I got 192BG RAM

    rocky2005809Jan 10, 2026

    @Prefo try asking chatgpt for a motion prompt followed by the action you want, this fixed it for me

    zhx03143302Jan 7, 2026· 6 reactions
    CivitAI

    Anybody try N S F. W content generation ? Asking for a friend 😉

    paul1978d696Jan 8, 2026· 1 reaction

    Hi everybody, I'm the friend ...

    MMOFanJan 8, 2026

    I'll follow this model, but without the "right" kind of loras it's a non-starter for me.

    AI_man2025Jan 8, 2026

    it is, as all this things are, trained on poisoned data to ensure censorship. High vram costs will likely prevent much lora training. (hope I am wrong) the default template on comfy Out of memory errored my 3090 on default settings. hence looking for a new workflow.

    bnzarev821Jan 8, 2026

    I've just tried a simple nsfw i2v with just some skin, the first 1-2 frames are your nsfw image and it instanlty fades into to a simple brown background, so it's lobotomised af - don't waste your time and just use Wan instead.

    EDIT: I was so wrong, another test generated a perfect NSFW (RIP Wan2.2): https://civitai.com/images/116853218

    janssenbuttonJan 8, 2026· 1 reaction

    @bnzarev821 you won't get any nsfw output without lora's but LTX2 definitely is not a waste of time. see my profile for latest uploads. not perfect but someting you won't pull off with wan that easy. (go fullscreen for audio)

    bnzarev821Jan 8, 2026

    @AI_man2025 works fine on 3060 for me, so you should absolutely have no problems with 3090. Just make sure you have set enough vitrual memory (google "pagefile.sys" for more info), mine in 200GB, but 300GB is even better if you have enough disk space

    janssenbuttonJan 8, 2026

    @bnzarev821 I'm using the default comfyUI ltx2 template. + the 40gb safetensor. (rtx 4090 + 192GB RAM). give it a try.

    jenniferhoustonpancakesJan 9, 2026· 1 reaction

    It's a massive memory hog and Distorch is out of the question. Fortunately ComfyUI has recently improved offloading to where's it's usable on Linux. The text encoder is also awful (like Qwen's) and to be usable it will need at least the fp8 abliterated version, if not a functional Q5. It's still too early to say.
    I should add that the 4-step upscale pass makes it look much, much worse. I am getting much better results just by doing everything at full res in one pass.

    MMOFanJan 9, 2026

    @janssenbutton your videos are very good, the ones with sound too. BUT, can you make vids where she's sucking a wang or are you relegated to just light fondling? Asking for me. Heh

    janssenbuttonJan 9, 2026· 1 reaction

    @MMOFan just like for wan back then, we need to wait for the amazing people training loras for this concept.

    5250571Jan 12, 2026

    @bnzarev821 what did you change? It lets me get pretty close but anything nude at all it sucks. Im using a custom character lora too.

    bnzarev821Jan 13, 2026

    @Artban69 I used the Kijai's "distilled" model "ltx-2-19b-distilled-fp8_transformer_only.safetensors" instead of the original "dev". You could also try "ltx-2-19b-distilled_Q8_0.ggup": https://huggingface.co/Kijai/LTXV2_comfy/tree/main/diffusion_models

    jakoc75648Jan 7, 2026· 1 reaction
    CivitAI

    Thanks for the workflow, the generation speed itself is incredible !

    oh_txtJan 8, 2026· 4 reactions
    CivitAI

    This workflow seems to produce worse outputs than the official workflow

    AI_man2025Jan 8, 2026
    CivitAI

    The text to video one I could not get to work, I need to look at that more but it looks like it is set up with aspecific scene in mind and thus specific lora's etc.

    The image to video one goes out of memory right at the start, on my 3090, on linux...i think this workflow is for 5090 only?

    rocky2005809Jan 10, 2026

    you can fix this by changing the height / width , lowering the length or the fps to 16

    carsten499Jan 9, 2026
    CivitAI

    How do you create longer videos?

    rocky2005809Jan 10, 2026

    Change the length by increasing it from 480 (19s video). Put a screenshot showing the length and fps in chatgpt then ask it to calculate the length for 10s, 15s, etc.

    Protagonist_NLJan 14, 2026

    if you have enough ram+vram, for 15 seconds type 15*24+1 in the frame int node

    grasshopper85116Feb 6, 2026

    @Protagonist_NL for a rtx 5090, what is the longest pength video you can do 1280x720p @ 16fps?

    Protagonist_NLFeb 6, 2026

    @grasshopper85116 i could render a 2 minute video, but i never do because in real filmmaking there are seldom scenes that last that long

    grasshopper85116Feb 6, 2026

    @Protagonist_NL somehow how i managed to render a 20 second LTX2 2560x1408 video @ 16fps in 13 minutes with my rtx 5090.

    The sharpenss of the output was amazing!! But after the generation my pc became almost unresponsive until I restarted it.

    rocky2005809Mar 24, 2026

    @grasshopper85116 20 sec is the sweet spot, if you go past that then youll see some weird shit

    sexgod1979Jan 9, 2026
    CivitAI

    thanks for the workflow!

    BrownRecluse666Jan 10, 2026
    CivitAI

    [enforce fail at alloc_cpu.cpp:121] data. DefaultCPUAllocator: not enough memory: you tried to allocate 146819089374594048 bytes.

    How do I fix this error?

    rocky2005809Jan 10, 2026

    Change the length by lowering from 480 (19s video) or changing the height / width or change to 16fps. Put a screenshot showing the length and fps in chatgpt then ask it to calculate the length for 10s, 15s, etc.

    RavirKunJan 10, 2026
    CivitAI

    how to solve this error? or my pc can't handle it? i'm on 3060 12gb vram and 16gb ram

    VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16

    no CLIP/text encoder weights in checkpoint, the text encoder model will not be loaded.

    Requested to load VideoVAE

    loaded completely; 9825.80 MB usable, 2331.69 MB loaded, full load: True

    E:\Comfy>echo If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest.

    If you see this and ComfyUI did not start try updating your Nvidia Drivers to the latest.

    E:\Comfy>pause

    Press any key to continue . . .

    ponystalk69990Jan 11, 2026
    CivitAI

    im waiting for ggfu checkpoint and gguf text encoder combo, tried doign meself, but got error

    kanginak161Jan 15, 2026
    CivitAI

    I have a 4090, 32gb ram, 24 vram and this workflow keeps on crash my entire pc, how can you all manage to generate with this?!

    ExcrutiatinglyExplicitJan 16, 2026· 2 reactions

    you need 32gb vram at least for the full model. Just buy an RTX Pro 6000 or use runpod or sth similar.

    haloJan 18, 2026

    run the ggufs

    Latent_DreamscapeJan 20, 2026

    @ExcrutiatinglyExplicit Or use ggufs or other methods to reduce vram usage within reasonable limits? XD

    @Latent_Dreamscape NEVER

    WItchesAIFeb 25, 2026· 2 reactions

    @ExcrutiatinglyExplicit "just buy an rtx pro 6000", "if you're homeless, just buy a house"

    jj43797771Jan 27, 2026
    CivitAI

    How do you run this with a gguf? the model loader only accepts full checkpoints, theres no unet loader that also does ltx audio vae

    berezka_dudeFeb 22, 2026
    CivitAI

    They always talk. It looks so stupid 😆

    kimmolehto859Feb 25, 2026
    CivitAI

    The stage1 sampler node has "output" and "denoised_output" and the "output" is connected to stage2. Is this intentional?

    Workflows
    LTXV

    Details

    Downloads
    5,719
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/7/2026
    Updated
    5/28/2026
    Deleted
    -

    Files

    ltx2WorkflowTextToVideo_v10.zip

    Mirrors

    HuggingFace (1 mirrors)