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
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 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
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.
@@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?
@@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
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?
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.
@@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 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?
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.
@@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.
You are the best, THANK YOU SO MUCH!!!!!!!!! Hands down one of the best AI channels.
Thank you for your support! Glad I could help.
Absolutely stunning ! Thank you !
Nice work dude. Very helpful, clear, and detailed tutorial. I really appreciate the effort that went into this.
Glad I could help!
Amazing vid, thx!
Glad it helped!
Really cool tutorial, detailed and clear, thank you
Thank you for watching, I’n glad I could help!
great video, thanks!!!
Whats the purpose of the block edit node and torch compile settings node (noob)? why not just use the lora select?
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
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..
Are you using the “Hunyuan Decode” node? There is a specific one for Kijai’s nodes
@@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
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.
@@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?
@@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
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?
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.
@@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!
Thanks for the advice! I’m brand new to creating on RUclips, so I am researching how to improve in the areas you suggested
Following your video, I encountered the following error: No module named 'hyvideo' Is there a solution for this error?
During Lora Training? Or during ComfyUI workflow?
@@TheArt-OfficialTrainer Lora
@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
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?
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.
@@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?
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.
@@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.
Do u have a discord or any type of contact/ socials so I can ask u questions if I struggle w things / need help?
Message me on my Patreon!
I’m thinking about creating a Discord in the future, but haven’t done it yet