kohya_ss on the sd3 branch is very usable, it need some tweaks but is getting there
kohya_ss on the sd3 branch is very usable, it need some tweaks but is getting there
Fi am still waiting him to fix
F
FHey Dr. Furkan do you have a good article on captioning/training photographic styles in SDXL?
Flike for types of lenses or lighting, stuff like that
Pjust change the res. i trained it many times. quality is super good. and it trains 3x times faster than xl.
Fnot yet sadly
Fautomatic1111 new version published : https://github.com/AUTOMATIC1111/stable-diffusion-webui/releases/tag/v1.10.0
GitHub
Features:
A lot of performance improvements (see below in Performance section)
Stable Diffusion 3 support (#16030, #16164, #16212)
Recommended Euler sampler; DDIM and other timestamp samplers cur...
A lot of performance improvements (see below in Performance section)
Stable Diffusion 3 support (#16030, #16164, #16212)
Recommended Euler sampler; DDIM and other timestamp samplers cur...
Dgreat!! thanks. I'm just finishing a test at 1024x1024
MHey guys, I have a question for you. When training a SD Model and the results turn out somewhat disformed. What could that be?
M
M
Fresolution mismatch
Fwhat do you train sdxl sd 1.5? whichn model
MXL Pony realism
Mtrained with 1024
Mrendered 1280:768
Mhey and nice talking to you. mr stablediffusionsuperman. thanks for your work 
Fpony must be the reason
Fdid you try 1024x1024 render?
Fsame issue?
Freal vis xl4 is very good for training a person
Maight. I will try that
Mi was wondering if it have to do with learningrate or bad captioning.
Mbut
Msame settings but 1024.
Mbut still deformed
Mill give realvis xl4 a shot :=
M
Fye try it
Fif still same problem
Fit could be related to dataset or training setup error
Mill give it another shot and report back
Mthanks
Fsure
JIs there any quality comparison between “roop” and “rope”?
Fi dont have any yet but you can 1 click install test. if you do let us know 
M@Dr. Furkan Gözükara do you still find using no xformers is still better\
Mconducted another 5 tests seems xformers is still not good
Mare your base input images all 1024x1024 or do you have different resolution images
_Could you please elaborate? How exactly could I try using it?
Fi didnt test
Fbut it is likely to reduce quality
Fin this tutorial you will see what i mean
FYouTubeSECourses
Welcome to the comprehensive tutorial on IP Adapter Face ID! In this detailed video, I unveil the secrets of installing and utilizing the experimental IP Adapter Face ID model. This model uniquely integrates ID embedding from face recognition, replacing the conventional CLIP image embedding. Whether you're a beginner or a pro, this guide is ...
Welcome to the comprehensive tutorial on IP Adapter Face ID! In this detailed video, I unveil the secrets of installing and utilizing the experimental IP Adapter Face ID model. This model uniquely integrates ID embedding from face recognition, replacing the conventional CLIP image embedding. Whether you're a beginner or a pro, this guide is ...F28:26 How to convert a custom CivitAI or any model into Diffusers on Kaggle to use
F20:58 How to convert CKPT or Safetensors checkpoints into diffusers on RunPod
F9:17 How to convert CKPT or Safetensors model files into diffusers format
Fstarting H100 and L40S to compare their CogVLM 2 speed test
FH100 is fast
