CivArchive
    AnimateLCM (Fast Video Generation) - v1.0Beta

    AnimateLCM

    LoRAs and Motion weights for fast video generation.

    We support high-quality video generation in 4 steps.

    Important Notes:

    1. Use LCMScheduler for sampling.

    2. CFG should be kept between 1 and 2. Use CFG 1 for saving memory and inference time. Use CFG > 1.5 and proper negative prompts for better visual quality.

    3. LoRA weights is set to 0.8 by default.

    4. 16 frames is preferred. Too long or too short videos tend to cause generation failure.

    For more details, please refer to https://github.com/G-U-N/AnimateLCM

    Please do tag our model #AnimateLCM if you use it.

    Links

    Contact: [email protected]

    [Paper]

    [Code]

    [Demos]

    Description

    FAQ

    Comments (21)

    AstralNemesisFeb 3, 2024
    CivitAI

    wow! really? would love to see a demo of this in action (on various hardware)

    G_U_N
    Author
    Feb 3, 2024

    That's a good point. We will try to do so.

    AstralNemesisFeb 3, 2024

    @G_U_N if what your describing is true, this is a real gamechanger.

    G_U_N
    Author
    Feb 3, 2024

    @AstralNemesis Hi AstralNemesis, thank you for your comment. In our work, we did not focus on hardware optimization. Instead, we reduced the sampling steps required for video generation from 25 to just 4, and we did this without needing classifier-free guidance. This means, under similar conditions, our method can achieve a generation speed that is approximately 12.5 times faster (calculated as 25 * 2 / 4). If you're familiar with LCM-Lora, you might consider our approach as its video equivalent.

    AstralNemesisFeb 3, 2024· 1 reaction

    @G_U_N I'm assuming this was training on high end hardware a 3090 or 4090 etc. I personally have a lowly 3060ti and have avoided video because of the longer render times, something like this could really level the playing field so to speak and really open up creativity and development.

    CyberTimonFeb 3, 2024
    CivitAI

    How do I use this in ComfyUi? Thanks - it looks awesome!

    macroFeb 4, 2024· 2 reactions

    yea .... same here .... the lora works but not the checkpoint

    guidenglongFeb 5, 2024· 2 reactions

    sd15_t2v_beta.ckpt is motion model

    rubirubsenFeb 7, 2024

    @guidenglong thanks for the hint. For everybody else wonderin where to get this:
    https://huggingface.co/wangfuyun/AnimateLCM/tree/main

    Thats the package I found, gonna try it out now.

    RunningFountainFeb 8, 2024· 1 reaction

    @macro same issue that I faced

    Josh_Ua124Nov 2, 2024· 1 reaction

    Same as @Macro & @RunningFountain , the lora works great but the chekpoint does not load, ive tried everything, throws following error ( AttributeError: module 'torch' has no attribute 'float8_e5m2' ) researching comes up with nothing useful, I verified im using the latest of everything, the few hits searching said certain things might be out of date, but they're not. Is the chekpoint expecting newest GPU speck or something? im on an older GPU.

    M14wMar 1, 2024
    CivitAI

    Hello, is there somewhere an explanation on how to use the Lora and how it is useful ?

    With it the picture have some heavy grain.

    Also do you have a suggestion of generative model to use with this motion module ?

    AIWarperMar 11, 2024
    CivitAI

    Any chance your team will be training an XL version of this? :D

    sfpsMar 21, 2024
    CivitAI

    Does it support prompt travel? It doesn't seem to change prompts over frames when using it in comfyui

    neuralkart19May 24, 2024

    May i know what is prompt travel?

    M14wApr 15, 2024
    CivitAI

    Do you actually know why this model is much better, at least with LCM generation ?

    kantoJun 9, 2024
    CivitAI

    The best animatediff lcm model sofar. Any plan to train more than 16 frames?

    lior007Jul 30, 2024· 1 reaction
    CivitAI

    HI. WHERE IS THE WORKFLOW?

    ManofDoom94Sep 24, 2024
    CivitAI

    Is this different from the original animatediff lcm motion module or is this just an old beta version? I see it says FAST video generation so is this a new trained lcm model?

    PookieNumnumsDec 10, 2024

    its the same, the original beta_t2v diff model

    Workflows
    SD 1.5

    Details

    Downloads
    4,382
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/3/2024
    Updated
    5/15/2026
    Deleted
    -

    Files

    animatelcmFastVideo_v10beta.zip

    Mirrors