yeah tried every combo of settings in MC with the l40, still like 10x slower for the 1.3b model than
yeah tried every combo of settings in MC with the l40, still like 10x slower for the 1.3b model than my 4090, so something is funky is going on.
VHey, I was wondering why I get an "RuntimeError: CUDA error: out of memory" in kohya when using your "lora training best flux configs" with 16GB and less. (have a 24 GB card, and the 24 GB configs do work! ... )
Scompared to 4070 ti super
Fyes definitely wrong
Fi got to sleep though tomorrow morning has lecture :d
Flet me check cuda counts
F5070 slightly better around 10%
F
Sdr Furkan that is he 5070 super ti? tht is the want i though could work for me, in price
Fi am not sure
Fif you can give me exact cuda numbers i can comment
Fbut i recommend 4090 second hand if you can find
For even 3090 ti
Fmore vram
Fvideo published
FYouTubeSECourses
Alibaba’s new Wan 2.1 text-to-video, video-to-video and image-to-video Open Source AI is unbelievable. In this tutorial I will show how you can install Wan 2.1 all publicly published models into your Windows PC with 1-click installation and use them with the easiest possible way. With the Gradio APP I have developed, you will be able to use Wan ...
FWriting Video chapters and manual fixing of Subtitles in progress
Fi got to go now 
FI plan to compare GGUF vs our APP tomorrow hopefully
Zwhenever you get a chance Dr, let me know how to speed up the generation time in MC, thanks!
Hopensource video models still have long way to go
Hthink about sd1.4 first release
Hand we got sd1.5 fine-tunes in just a year
Hquality improvements are just incredible between sd1.4 and sd1.5 fine-tunes
Hwe gonna see better, faster and local video models by end of 2025, im totally sure with that
AThis one I made is slightly better restoration, but not by much!
TFound it on X. How true not sure, but need more investigation.
JRegarding upscaling in swarmui, what is the 4xrealwebphoto model that you use in tips-info @Dr. Furkan Gözükara ? Or which one is the best to use (for realistic portrait photos)
Hinterestingly enough, training a ~250 image dataset on wan2.1 14b "only" takes 27gb gpu at res 1024 and rank 128, I wonder how far it can be pushed with a 80gb gpu
Hbut to be fair it's quite slow per iteration (~23sec)
Hneed to try videos next but I really want to push that training to the max
HBUT the lora is 1gb damn
Fthis guy doesnt know
Fhe confused telemetry data 
Fit is here
FOpenModelDB
OpenModelDB is a community driven database of AI Upscaling models. We aim to provide a better way to find and compare models than existing sources.
Fmy unified downloader also downloads it
Fhow good it works?
Fi plan make a gui for this
Fby the way sd 3.5 large training getting improved. now we gonna have trained clip l and clip g into embedded file
HI'm still training, it's very slow but it works well on a A6000, I've not trained videos yet but I will work on it this week end, but it's promising tbh, the lora file is 1gb tho, I'm waiting for a few epoch and will test and let you know
F1gb is not big
HFor a lora ? Would you recommend going rank 256 ? I don't really care about the size or the time it takes to train tbh, as long as the results are there
F128 usually great
DIs this WAN?
AFreally good
TAre you planning to research gguf for flux dev as well?
Fyou mean compare gguf of flux vs like fp8 or bf16?
Tyep, and also a tutorial on how to use it in swarmUI