I'm using comfyui right now and I think I hate it
I'm using comfyui right now and I think I hate it
Fincrease max new tokens
Fuse swarmui :d
Fi am gonna train a community lora with unsplash dataset i have
F10400 images
Fwill caption with joycaption and share dataset on patreon 
Factually it will be 20800 images since i will include bucketing version as well
Ijesus
PHey @Dr. Furkan Gözükara 
I’m trying to install CUDA 11.8 on RTX 4090 for training flux.
Every time I try to install it fails. I’ve tried a couple of different versions but still no luck.
I’m using windows 11 pro, with Nvidia studio driver version 531.41
I’m trying to install CUDA 11.8 on RTX 4090 for training flux.
Every time I try to install it fails. I’ve tried a couple of different versions but still no luck.
I’m using windows 11 pro, with Nvidia studio driver version 531.41
AI myself have glasses and trained a lora with 20/25 images with glasses, it always puts them by default. Have not used captions tho because I trained using ai-toolkit on replicate.
One issue I have isit always puts my face on other people in the background too and is heavily influenced by the background I had on the input training images (old city buildings)
One issue I have isit always puts my face on other people in the background too and is heavily influenced by the background I had on the input training images (old city buildings)
K@Dr. Furkan Gözükara can you please add the option in joy caption to cut off the last sentence. It’s always cut off at the end. So and option to cut of the last one would be perfect.
Ninteresting. maybe a bit overtrained then? you could try a version of the lora based off fewer epochs\steps if ai-toolkit saves them along the way? or specify a background in your prompt?
AYes totally, when specifying backroung in prompt it does work as intended
AI used 2200 steps in training v2, and 1000 for v1
ABoth are the same in results tbh
SDoes anyone have different/worse results with Flux LoRA’s in Comfy than in Forge for example?
�yeah when I tested loras out in forge they wouldn't have any effect at all most of the time, even with the trigger word in prompt, but in SwarmUI they worked flawlessly so I dunno what's happening there
TAfter the installation is complete, press 1 to start the error
T
T@Dr. Furkan Gözükara
Fhow it fails exactly? nvidia has setup
Fsure let me try that option
Fi will also add multi gpu to joy caption app
Fi need to see install logs
Freinstall and send me logs
K@Dr. Furkan Gözükara would you also be making a internvl2 gradio app? Seems that’s the best caption model right now
KTried some comparisons between samplers and schedulers on my new LORA
KAll other combinations except these were somewhat useless!
FPatreon
Get more from SECourses: Tutorials, Guides, Resources, Training, FLUX, MidJourney, Voice Clone, TTS, ChatGPT, GPT, LLM, Scripts by Furkan Gözü on Patreon
F
Fany demo of this like on hugging face?
Fi think unipc normal best
KYes it's good
KNormally... Doesn't work at all now
DI posted on github asking for Flux CLIP_L Text Encoder
KDon't know why
KHeun+Simple was really good now
DI was asking about CLIP_L but hes talking about T5... adk
Malready spoke to sd scripts kohya, he is is working on clip l text encoder training
Mt5 will be frozen at all times
Mthink they're talking about this one mentioned earlier - https://huggingface.co/spaces/OpenGVLab/InternVL
Fit is api based
Fthere is no code at that app
Dyes T5 is too large
Fi am adding multi gpu to joycaption app
Feven flux authors didnt train it
Fso unnecessary
KThis one here
KJoycaption... Gotta try that one