LTX Video 0.9.1 With Flow Edit Video2Video - A Game Changer For Local AI!

Поделиться
HTML-код
  • Опубликовано: 26 дек 2024

Комментарии • 40

  • @TheFutureThinker
    @TheFutureThinker  2 дня назад +6

    ComfyUI-LTXTricks
    github.com/logtd/ComfyUI-LTXTricks
    Attached workflows of 2, LTX with STG and LTX Flow Edit V2V (Freebies):
    www.patreon.com/posts/ltx-video-0-9-1-118605761?Link&

  • @trung_ai
    @trung_ai 2 дня назад +4

    Thank you for a great video. I would like to add some of my findings with I2V after exploring LTX (0.9.0):
    - With mp4 compression, for realistic video, optimal CRF value is ~ 30, 50 60 will degrade quality a lot and cause diverse and extreme motion. For art and anime, there is usually no need for detailed texture so if you want more motion CRF 50 will yield more diverse animation
    - For prompting, keywords like slowly, gradually will make smoother and more consistent animation but the output will quite in slow motion, so interpolate and increase FPS is a good choice. Add very slowly will make it even slower.
    - LTX is very good at landscape/ video without people. So I2V or T2V with detailed prompts most of the time will yield great results.
    - Don't include multiple or sudden camera movement keywords (e.g. shift, suddenly etc.) as it will create morphing animations (i.e. from frame 0 to 20 it has consistent video, then will suddenly shift to entirely different scenes)
    - For dancing/ more rapid character movement, I have good results with this kind of prompt "[Subject] begins to dance with graceful precision, his movements fluid and intentional".

  • @ratside9485
    @ratside9485 2 дня назад +5

    Loras are also possible, the model really has potential. I believe they have now also announced official Lora support.

    • @AIBusinessIdeasBenji
      @AIBusinessIdeasBenji 2 дня назад +2

      I know a guy even fine tune this base model. And it awesome! Next video talk about this.

    • @TerragonAI
      @TerragonAI 2 дня назад

      @@AIBusinessIdeasBenji that sounds great! 🙂

  • @mhnoni
    @mhnoni 16 часов назад

    Thanks for the video, What is the min vram for this?

  • @insurancecasino5790
    @insurancecasino5790 2 дня назад

    Bro, your channel is going to give me a heart attack. LOL! You're a machine with these vids updates. Awesome work.

    • @TheFutureThinker
      @TheFutureThinker  2 дня назад +3

      hehe.. thanks. Have fun on holiday!
      I will continue with the web app development for Hunyuan Video Web UI. ;)

  • @trung_ai
    @trung_ai 2 дня назад

    I have tried LTX quite a few times already, overall has great experience with it. Though one thing I struggle with is camera movement, e.g. zoom out/ pan right/ pan left etc. doesn't seem to work. Have you found a consistent method for camera movement?

    • @TheFutureThinker
      @TheFutureThinker  2 дня назад

      It need a very detail prompt for camera panning. and version 0.9.1 does improve on prompt following.
      Good luck ;)

  • @dsphotos
    @dsphotos День назад

    great channel! thx a lot but i have 1 error at the end of the flow:
    ImageConcanate: Sizes of tensors must match except in dimension 2. Expected size 111 but got size 105 for tensor number 1 in the list.

    • @dsphotos
      @dsphotos День назад

      just deledet the compare nodes, since i dont need it now error is gone, also noticed if you tell in your prompt to move slowly and use 30fps + steps 40-50+ in sheduler you get a much better result-> still renders it quite fast, which is amazing on a 10 years old pc + rtx 3060 with 12gb ram :-)

  • @ckhmod
    @ckhmod 2 дня назад

    Great video! One question. Where does Florence-2-Flux-Large install to?

    • @TheFutureThinker
      @TheFutureThinker  2 дня назад +1

      models\llm\Florence-2-Flux-Large
      it can be download in here manually : huggingface.co/gokaygokay/Florence-2-Flux-Large/tree/main
      Or use Download Florenece 2 Loader node, auto download.

    • @ckhmod
      @ckhmod 2 дня назад

      @@TheFutureThinker Thank you so much! Just going through this now. Cheers.

  • @Gardener7
    @Gardener7 2 дня назад

    Which is better, this one or the Nvidia one?

  • @kalakala4803
    @kalakala4803 2 дня назад

    Great vid ! We have V2V that to be run on PC friendly like AnimateDiff before!

  • @HugoCostaBR
    @HugoCostaBR 2 дня назад

    The LTX-Video Node is still broken in Comfyui Manager Installer. The only way is to install manually via Git URL.

    • @sorijin
      @sorijin 2 дня назад

      Nope. While it doesn't show up in the Install Missing Custom Nodes, it is searchable to install from Custom Nodes Manager and works 100% when installed from there.

  • @seifergunblade9857
    @seifergunblade9857 2 дня назад

    what is the minimum vram

  • @TheKr4tosD
    @TheKr4tosD 2 дня назад

    hello, anyone can help me ? its getting this error: Missing Node Types
    When loading the graph, the following node types were not found
    Florence2ModelLoader

  • @FusionDeveloper
    @FusionDeveloper 2 дня назад +1

    in my experience so far, LTX 0.9.1 has higher VRAM requirement than LTX 0.9, even though 0.9.1 is half the size.

  • @wonder111
    @wonder111 2 дня назад

    Anyone else getting cross-hatching in moving highlight areas like a flickering flame? Looking for solutions in DaVinci Resolve. Topaz upscale seems to ignore cross-hatching. I was wondering if I should optimize footage in Resolve before upscaling in Topaz? Anyone else working in this way?

  • @Chaz-x1i
    @Chaz-x1i 2 дня назад

    Sadly, like with the LTX text to video it comes out horribly deformed. I put a 4 second video I made with Hunyuan, which turned out perfectly, of Snow Site petting a fawn and I put in the prompt "snow white petting a small red dragon with wings". It came out with Snow White's head being oversized and the dragon looking like a grossly deformed aardvark. LTX is just garbage, bro. It's fast, yeah, but at the sacrifice of anything looking remotely normal. Also, virtually none of the LTX workflows I found ever worked, usually because of something about "missing 1 required positional argument: 'attention_mask", which I have no idea what it means or how to fix it. The only Comfy video thing that ever worked properly and with good results is the Hunyuan one. LTX stuff will just drive a person insane.

  • @thedevo01
    @thedevo01 2 дня назад

    The guy in the apocalyptic city wouldn't be able to walk with a knee like that 😆
    Jokes aside tho, in curious why it ignored the boy turning 180 while walking away from the camera.

  • @petergreene8760
    @petergreene8760 2 дня назад

    I can't seem to 0.9.1 model to run on my 2080ti without getting OOM error

    • @TheFutureThinker
      @TheFutureThinker  2 дня назад

      2080ti ? Have you emailed LTX ask why it happened?

    • @petergreene8760
      @petergreene8760 10 часов назад

      @TheFutureThinker no, I didn't think to do that

  • @dropLove_
    @dropLove_ 2 дня назад

    Benji stays on it.

  • @luisellagirasole7909
    @luisellagirasole7909 2 дня назад +1

    Hi, I got always this error
    "Error(s) in loading state_dict for VideoVAE:
    size mismatch for decoder.conv_in.conv.weight: copying a param with shape torch.Size([1024, 128, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 128, 3, 3, 3]).
    size mismatch for decoder.conv_in.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.weight: copying a param with shape torch.Size([1024, 1024, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 512, 3, 3, 3]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv1.conv.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([512]).
    size mismatch for decoder.up_blocks.0.res_blocks.0.conv2.conv.weight: copying a param with shape torch.Size([1024, 1024, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 512, 3, 3, 3]). etc"

    • @TheFutureThinker
      @TheFutureThinker  2 дня назад +1

      Check out 02:20 . VideoVAE error because you need the new VAE loader for the version 0.9.1 model VAE archecture.

    • @luisellagirasole7909
      @luisellagirasole7909 2 дня назад

      @@TheFutureThinker Yes I have update comfyUi from manager, but still got error, maybe I will update in another way, I'll try, thanks

    • @TheFutureThinker
      @TheFutureThinker  2 дня назад

      Try not to use ComfyUI manager to update if that is the case. Git pull.

  • @MaxCui-jt8ob
    @MaxCui-jt8ob 2 дня назад

    CR 文本替换
    “list”对象没有属性“replace”

  • @phudo1910
    @phudo1910 2 дня назад +1

    Very hard to control the output result. This is curently not the game changer as you said.

    • @TheFutureThinker
      @TheFutureThinker  2 дня назад

      depends how you use it, if you said control? like a video editor? it won't be. it's AI.

    • @darmok072
      @darmok072 2 дня назад

      Have you used something that gives greater control? Personally I find everything pretty much the same at the moment: just with different ways of getting to the same results.