you can't cache text encoder on bmaltais
you can't cache text encoder on bmaltais
Fwhat do you mean
MFile "D:\kohya_ss\sd-scripts\flux_train_network.py", line 514, in <module> trainer.train(args) File "D:\kohya_ss\sd-scripts\train_network.py", line 441, in train self.post_process_network(args, accelerator, network, text_encoders, unet) File "D:\kohya_ss\sd-scripts\flux_train_network.py", line 168, in post_process_network raise ValueError( ValueError: T5XXL is trained, so cache_text_encoder_outputs cannot be used / T5XXL学習時はcache_text_encoder_outputsは使用できません
MFi think cache is for when we dont train t5
Fnot sure
Myeah without it, you need 48gb vram gpu
Mgot it working with split mode single
WWhere do I change the 1024 to 512?
Fsearch this keyword on gradio of kohya : Max resolution
WI did that, but it didn't do any training then.
WINFO [Dataset 0] train_util.py:2326
INFO caching latents with caching strategy. train_util.py:984
INFO checking cache validity... train_util.py:994
100%|██████████████████████████████████████████████████████████████████████████████████████████| 14/14 [00:00<?, ?it/s]
INFO caching latents... train_util.py:1038
0%| | 0/14 [00:00<?, ?it/s]18:14:23-407701 INFO Training has ended.
INFO caching latents with caching strategy. train_util.py:984
INFO checking cache validity... train_util.py:994
100%|██████████████████████████████████████████████████████████████████████████████████████████| 14/14 [00:00<?, ?it/s]
INFO caching latents... train_util.py:1038
0%| | 0/14 [00:00<?, ?it/s]18:14:23-407701 INFO Training has ended.
W
Fuse v27 configs
Fwe fixed thisd
Falso set accelerator
FYouTubeSECourses
Many people having issues due to inaccurate Accelerate setup. This is how to setup to make it work properly
1-click installers and best configs for Kohya FLUX training :
A Big complete tutorial very soon hopefully : https://www.patreon.com/posts/kohya-flux-lora-110293257
1-click installers and best configs for Kohya FLUX training :
A Big complete tutorial very soon hopefully : https://www.patreon.com/posts/kohya-flux-lora-110293257
WThank you!
Fwow i couldnt do anything but just reply patron messages entire day 
Finstalling all rope main versions to verify them
LGuys I installed SwarmUI today to try and test Flux Lora, but the Unet folder was not in my models folder. I added it and ran the model download script. But I only see one model. Also when generating with the Lora I get an error
LRuntimeError: .to() does not accept copy argument
LI'll just delete and try to install again, it missing the unet folder and not loading the models makes me suspect an install issue
Fthey changed folder name
Fbut unet stil works
Fmanually genereate it
Fput models there
Fneww folder name is diffusion_models
JHi @Dr. Furkan Gözükara , After i generated lora of product images with flux, its gving amazing results. Thanks a lot for great explainer video, this is promising to solve my long term problems on realistic product images,
How can i Dictate swarm not to change the size and color of trained product image while generating the final images.?
How can i Dictate swarm not to change the size and color of trained product image while generating the final images.?
GWhere do I post?
TI now use SOLAR-10.7B-Instruct-v1.0-uncensored-GGUF to generate prompt for Flux and it’s night and day, my generated images are incredible.
Gwhat is that
Gshare samples
TIt’s a LLM. Basically you type : generate prompt for « a man riding a bicycle in the street » and it generates a very long prompt with many details
TI use this node https://github.com/SeargeDP/ComfyUI_Searge_LLM
GitHub
Custom nodes for ComfyUI that utilize a language model to generate text-to-image prompts - SeargeDP/ComfyUI_Searge_LLM
T
V@Dr. Furkan Gözükara i still cannot understand your new post of kaggle swarmUI, I have sent you a private message
Shello, guys, please tell me: to make cool realistic photos of myself flying like superman I need to use 2 loras? 1 of myself and 2nd is realism lora?
Fyou need a better dataset for it
FGitHub
Contribute to kohya-ss/sd-scripts development by creating an account on GitHub.
Fi replied try to figure out logic easyt
Fyou can just train on flux and sufficient
Mhello if i want to train a flux lora and try 32 network rank should my network alpha be 32 or 1
Min sdxl i used to set it to 1
FSince if alpha is not set equal a new LR needs to be researched
Mthank you
Mis "Rank_3_18950MB_9_05_Second_IT" config for gpus with 24gb vram bf16 or are only the configs for 48gb vram bf16?
Frank 3 is for 24 gb
Frank 1 and 2 for 48gb
W@Dr. Furkan Gözükara Using the Rank5 and the latest Torch 2.5, I'm trying to train, it gets here and then just seems to not be doing the training. Also even though it says it uses less memory, my GPU is still using 23.37g out of 24.
