Create Your Own Hunyuan Video LoRA (Under 20GB of VRAM Possible!!)

Поделиться
HTML-код
  • Опубликовано: 5 янв 2025

Комментарии • 35

  • @PhantasyAI0
    @PhantasyAI0 9 дней назад +2

    You are the best, THANK YOU SO MUCH!!!!!!!!! Hands down one of the best AI channels.

  • @Falkonar
    @Falkonar 8 дней назад +1

    Absolutely stunning ! Thank you !

  • @nemesisleather
    @nemesisleather 8 дней назад +1

    Nice work dude. Very helpful, clear, and detailed tutorial. I really appreciate the effort that went into this.

  • @gjohgj
    @gjohgj 4 дня назад +1

    Amazing vid, thx!

  • @dewabrata83
    @dewabrata83 7 дней назад

    Really cool tutorial, detailed and clear, thank you

  • @miken3d
    @miken3d 6 дней назад +1

    great video, thanks!!!

  • @Jutochoppa1
    @Jutochoppa1 5 дней назад

    Whats the purpose of the block edit node and torch compile settings node (noob)? why not just use the lora select?

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  5 дней назад +1

      They help save VRAM! With Kijai’s custom nodes, If you don’t use torch compile and block edit, you won’t be able to fit the full 720x1280x129f on 24GB VRAM with those nodes, I think you can fit the full resolution into

  • @toketokepass
    @toketokepass 5 дней назад

    When ever I try to run the Hunyuan video wrapper workflow to use loras, I get this error: "Error(s) in loading state_dict for AutoencoderKLCausal3D:
    Missing key(s) in state_dict: "encoder.down_blocks.0.resnets.0.norm1.weight etc.." - where as when I use the native Hunyuan workflow I get no such error. Im wondering if I need a different vae or something..

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  5 дней назад

      Are you using the “Hunyuan Decode” node? There is a specific one for Kijai’s nodes

    • @toketokepass
      @toketokepass 4 дня назад

      @@TheArt-OfficialTrainer Im using all the Kaji specific nodes, though I think Ive figured out the issue - I dont have sageattention and triton installed and they look like a pain to

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  4 дня назад +1

      You don’t need to use sageattention, you can just use flash attention in that dropdown instead. I’m not sure whether Triton is required if you don’t use sageattention.

    • @toketokepass
      @toketokepass 4 дня назад

      @@TheArt-OfficialTrainer I didnt have flash attn installed either, so i used comfy attn which seems to be preinstalled. is there a big difference between sage, flash and comfy attn?

    • @toketokepass
      @toketokepass 4 дня назад

      @@TheArt-OfficialTrainer Cheers for your help so far man. Im currently trying to get kijai's img2vid working (IP2V) but get this error AttributeError: 'LlavaForConditionalGeneration' object has no attribute 'final_layer_norm' .. Chat gpt seems to think this is related to not having a transformers lib installed, but there was no mention of needing to install a transformers lib on kijai's git page

  • @yiyo4375
    @yiyo4375 9 дней назад

    Do you think there's a way to do this on a 4090 Mobile? The PC only has 16gb of vram. Do you think it's possible to share the extra load on CPU, RAM or SSD or train with lower resolution, or does the vram consumption not allow it. Or's there a training app that will allow me to do this?

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  8 дней назад

      I think that you could probably train with 512x512 images, maybe even up to 768x768. Just make sure you change the frame bucket size to [1] in the dataset.toml file. If I get some time today, I’ll try it out and see how much VRAM image training used and include that in the description.

    • @yiyo4375
      @yiyo4375 8 дней назад

      ​@@TheArt-OfficialTrainerI would appreciate it very much. Dude I want to comment to you that many in the community think that training loras for Hunyuan requires a minimum of 40gb of Vram. And progress has been stagnant. If you could improve the SEO of your video and put tags, thumbnail and title more attractive maybe we can change that and more people are encouraged to make loras and improvements to this video generator!

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  8 дней назад +1

      Thanks for the advice! I’m brand new to creating on RUclips, so I am researching how to improve in the areas you suggested

  • @임수경-e5v
    @임수경-e5v 7 дней назад

    Following your video, I encountered the following error: No module named 'hyvideo' Is there a solution for this error?

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  7 дней назад

      During Lora Training? Or during ComfyUI workflow?

    • @임수경-e5v
      @임수경-e5v 7 дней назад

      ​@@TheArt-OfficialTrainer Lora

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  6 дней назад

      @임수경-e5v can you share the actual error? I would guess either you’re missing a package or the path to your hunyuan video model is incorrect

  • @Chaz-x1i
    @Chaz-x1i День назад

    I have a better idea, you make the loras and then make them available for download, because who has $1600 for a 24 GB rig?

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  День назад

      Training a lora this way should only cost $3 max! There are too many Lora possibilities for me to create all the ones that people want.

    • @Chaz-x1i
      @Chaz-x1i День назад

      @@TheArt-OfficialTrainer How, by renting GPU online? What would happen if I tried to do it with a RTX 3060, just take a long time or not even possible?

    • @TheArt-OfficialTrainer
      @TheArt-OfficialTrainer  День назад

      Yeah, this tutorial uses RunPod. On a 3060, there’s a chance you could train using 512x512 images. And if that doesn’t work, you could even try 256x256. Just make sure to adjust the bucket size correctly.

    • @Chaz-x1i
      @Chaz-x1i 15 часов назад

      @@TheArt-OfficialTrainer Thanks. I found there actually are a bunch of Hunyuan LoRAs available on CivitAI anyway, though if I ever do want to make one your video will come in handy.

  • @mohammedAli-h9p7d
    @mohammedAli-h9p7d 3 дня назад

    Do u have a discord or any type of contact/ socials so I can ask u questions if I struggle w things / need help?