Software Engineering Courses (SECourses)•10mo ago

so 3 picture in total to get what I want

AAiInfluence so 3 picture in total to get what I want

Furkan Gözükara SECourses•2/27/25, 2:12 PM

i didnt get what you mean

Furkan Gözükara SECourses•2/27/25, 2:12 PM

if anyone has good wan 2.1 video please send me

Furkan Gözükara SECourses•2/27/25, 2:12 PM

i can put to tutorial

HRK•2/27/25, 2:49 PM

Hey all, I've played around to try training loras on Wan, I cannot get Diffusion-pipe to work, it never finds the config file, and i've tried DiffSynth, which works but only accepts videos.

I wondered, is there a 3rd alternative ? And as it seems i'm currently stuck with DiffSynth, we do agree the dataset must be videos max 720x1280 of 81 frames at 16fps, right ?

HHRK Hey all, I've played around to try training loras on Wan, I cannot get Diffusion...

Furkan Gözükara SECourses•2/27/25, 2:52 PM

i plan to make a tutorial based on DiffSynth wan training

Furkan Gözükara SECourses•2/27/25, 2:53 PM

i am not sure about dataset though :d

HRK•2/27/25, 2:54 PM

Yeah it's not super clear, but I cannot make image work in training, the data process step returns this : "AttributeError: 'LegacyReader' object has no attribute 'count_frames'", I'm not a tech wizard but to me it means no images and only videos ahah

FFurkan Gözükara SECourses i am not sure about dataset though :d

HRK•2/27/25, 2:55 PM

Currently testing a little training with proper dataset for wan, I will let you know how it goes if that helps

FFurkan Gözükara SECourses i didnt get what you mean

AiInfluenceOP•2/27/25, 3:00 PM

I'll explain later on currently testing

HHRK Hey all, I've played around to try training loras on Wan, I cannot get Diffusion...

AiInfluenceOP•2/27/25, 3:00 PM

I thought you couldn't train yet?

AAiInfluence I thought you couldn't train yet?

HRK•2/27/25, 3:05 PM

not on diffusionpipe, the config file is apparently never found, but I can on diffsynth, but I can't train with images on diffsynth, only videos

HRK•2/27/25, 3:07 PM

so that's kinda annoying, I can't retrain some of the Hunyuan datasets I have with DiffSynth, which were only images

HRK•2/27/25, 3:16 PM

ok I'm super super dumb I forgot to remove a " / " in the config file which made the whole thing go mad for the config.json file, diffusionpipe works

Going to try different video formats and frame length etc and will let you guys know if it can help

HHRK ok I'm super super dumb I forgot to remove a " / " in the config file which made...

Furkan Gözükara SECourses•2/27/25, 3:34 PM

awesome please do

Zaulinator•2/27/25, 4:21 PM

signing up for Massed Compute until my ram comes in. getting annoyed of the long load times lol

FFurkan Gözükara SECourses awesome please do

HRK•2/27/25, 4:26 PM

So i've barely scraped the surface but on diffusion-pipe I've tried simple videos at 16fps. Following the num_frames from the empty embeds node from Kijai, I've used 16n+1 number of frames, (17, 33, 49, 65, 81, 129). I added all these in the frame_bucket part of the dataset.toml to be safe, so it looks like that : frame_buckets = [1, 17, 33, 49, 65, 81, 129] (1 is for Images I guess).

Basically everything got processed but not the 129 frames clip, i suppose it's too long.

Running on linux on a 4090, I can train the lora at rank 128, resolution 704, and it uses around 19gb of the gpu. All that training on the wan 1.3b model. I've tried 1024 training but it ooms instantly. (knowing my system was taking 400mb, I don't think it's possible to train 1024 at all on a 4090)

HRK•2/27/25, 4:41 PM

and with the exact same parameters, when using only images in the dataset it seems faster than hunyuan and uses only 14gb vram

Need to test on the 14b model but it's all promising

Zaulinator•2/27/25, 4:55 PM

@Dr. Furkan Gözükara im getting some pretty slow speeds with an L40 through Massed compute - do i need to change any settings?