okay also 1.5 ckpt training, right? i have to retrain models
okay also 1.5 ckpt training, right? i have to retrain models
Fgive it a try notebook on patreon
Vokay let me go over it now, thanks a lot
Wyes it's in the stable diffusion folder and I did restart.
Fplease ask in developer discord he answers all
F
O(Updated both versions, both 0.1 and ComfyConverted are the same file now. please redownload.) Deep Semantic Comprehension: Flux+ Detailer excels i...
Awhat is this? and how doi fix it?
Danyone else wondering if SD has a reaction to flux?
TFlux only works good with euler simple?
RIt also works with deis sampler and with the beta scheduler - I didn’t see much difference between them though
Fthey said gonna publish sd 3.1
Fi am waiting
Fi havent tested yet i should test
HSd3.1 will still only be 8b vs flux at 12b right?
Fno ideas
Fi also dont expect much
Fflux is many levels better than anything else
TIn MC there is some kind of error with Forge, when I put the arguments export COMMANDLINE_ARGS="--xformers --share --enable-insecure-extension-access" there is no way to start it, the console closes by itself. I think the problem is with xformers.
Tyes, the problem is with xformers 100%, with the other arguments work
Fye with latest version xformers not working
Ffor everyone
Ftesting 2 new configs for onetrainer
Fdoing 4 th training
F3 with one trainer 1 with kohya for sdxl
Fperfecting it before moving to flux :d
Vwhen will you create LORA training for flux? and did you try the latest flux nf2 v2 model? and do you think flux is totally going to replace stable diffusion? sd 1.5 and sdxl...
Fi am waiting kohya to start trainings
Ftesting all configuration
Fi think flux will replace all 
Fi also tested flux nf2 v2 and added into downloader
FPatreon
Get more from SECourses: Tutorials, Guides, Resources, Training, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözükara on Patreon
Fi am waiting swarmui to add new quants to test them too
Vmy friend has bought rtx 4090 . he told me i can use his gpu..waiting for you video
Fand i am waiting kohya
FFafk
Vi am not afk
PHi @Dr. Furkan Gözükara ,
I need to develop some low quality picture of before and after images. When i say low qiality, it cannot be the level level of high quality picture that we can create in midjourney. This is what we need for a campaign.
I need to develop some low quality picture of before and after images. When i say low qiality, it cannot be the level level of high quality picture that we can create in midjourney. This is what we need for a campaign.
PI wnated to ask if there's a way to acheive this?
PFor example some thing like this
Pwell SD 3 2B vs Flux 12b and SD 3 has still better quality. If anatomy wasnt broken - i would prefer sd 3 for photo realistic things. I just cant get over SD 3 visual quality. so i`m waiting for 3.1 a lot...
HI think SD3.1 could have some cool uses. Flux training has been going well for me, I can see finetunes make photorealism much better rather quickly
Pits possible. Lykon says VAE 16 ch but FLux was just trained on MJ images and 3.0 on real photos. If thats the case - we can theoretically get flux to be as detailed as sd 3
Pi tain with ai-toolkit. But qulity of anatomy degrades as well as ability for text...for some reason (Lykon also said on twitter that would happen...) waiting for Kohya
HYeah I was using simpletuner.... It was fun to learn but im waiting for kohya now as well
HMy lora definitely caused some anatomy issues in the hands
Dcivitai has flux lora training now
Dearly results seem promising
