I agree Doc, I am also against it but I was asked to help with this request. If without NSFW, what w
I agree Doc, I am also against it but I was asked to help with this request. If without NSFW, what would be the best way?
Fkaggle works for SDXL and SD 1.5 training
Pbut based on this video https://www.youtube.com/watch?v=FvpWy1x5etM I concluded that Flax Fal Fine tuning has much better detailing. If you compare SDXL and SD 1.5, the XL version will win in detailing by a lot. Honestly, I am very grateful for your work and contribution to the development of neural networks.
YouTubeSECourses
If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...
FFLUX is 10 times better than SDXL
GHi everyone and @Furkan Gözükara SECourses
I have a paired dataset with images before and after retouching (color correction, defect removal on face and body, skin color amelioration). I want to train a generative model to automate this process at scale.
Would Pix2Pix (GANs) be the best choice, or are diffusion models, flux , vision transformers, or other supervised methods better for high-fidelity, production-ready retouching?
Looking for insights on the most effective approach. Thanks!
I have a paired dataset with images before and after retouching (color correction, defect removal on face and body, skin color amelioration). I want to train a generative model to automate this process at scale.
Would Pix2Pix (GANs) be the best choice, or are diffusion models, flux , vision transformers, or other supervised methods better for high-fidelity, production-ready retouching?
Looking for insights on the most effective approach. Thanks!
Fsadly i dont know what can be best way for automating atm
UHi @Furkan Gözükara SECourses ,
I need some advice as I have been struggling with Lora training for a product. I tried with and without captions (without was worse).
I need some advice as I have been struggling with Lora training for a product. I tried with and without captions (without was worse).
Problems I'm Facing
- Trigger words don't work consistently. For example, if I use "KOKUMKF2512NVYP2," sometimes I get some kind of device (see trigger_word_image) and sometimes a dress but with different colors and the same pattern.
- When I use prompts where I explain the dress and background, I get a blue dress, but each time the dress color appears in different shades.
- Hands are distorted a lot.
- When I prompt it to generate on different body types, it doesn't work.
No Caption Lora:
Captioned Lora (see screenshot for dataset):
Mixed Lora of cloth and model head (see screenshot for dataset):
UThank you so much for doing amazing research and sharing with us. And Sorry for the little long message I just want to share as much detail as possible. And is full finetuning is a good choice for this specific use case or not?
Here is some more details:
For the dataset:
Dress: 16 images
Model/Person: 9 headshot images generated by comfy consistent character workflow
I also tried using both lora (dress and person) to create images in SwarmUI but results are disappointing. The major importance for me is to get the pattern of dress, color of dress and person wearing wearing that dress. Please let me know If you need any other details. Please guide me to the right direction. Thanks again
Here is some more details:
For the dataset:
Dress: 16 images
Model/Person: 9 headshot images generated by comfy consistent character workflow
I also tried using both lora (dress and person) to create images in SwarmUI but results are disappointing. The major importance for me is to get the pattern of dress, color of dress and person wearing wearing that dress. Please let me know If you need any other details. Please guide me to the right direction. Thanks again
H@Furkan Gözükara SECourses hey, really enjoyed your videos.
would appreciate a deep-dive comparing the following methods:
would appreciate a deep-dive comparing the following methods:
- full dreambooth on flux (extremely memory intensive)
- dreambooth lora on flux
- full dreambooth on flux + then extract the lora via SVD
- plain flux lora
- plan flux full finetune
J@Furkan Gözükara SECourses I am trying out dreambooth training on runpod using your guide. I got it to run but out of memory on a 4090.
Any guidance would be helpful.
------------------------------------
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 48.00 MiB. GPU 0 has a total capacity of 23.64 GiB of which 20.81 MiB is free. Process 3037847 has 23.62 GiB memory in use. Of the allocated memory 23.08 GiB is allocated by PyTorch, and 86.61 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)"
Any guidance would be helpful.
------------------------------------
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 48.00 MiB. GPU 0 has a total capacity of 23.64 GiB of which 20.81 MiB is free. Process 3037847 has 23.62 GiB memory in use. Of the allocated memory 23.08 GiB is allocated by PyTorch, and 86.61 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)"
Fhey your trigger word is wrong. it is many multiple words combination
Fi recommend watch this video no skip
FYouTubeSECourses
If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...
Fi already did and full dreambooth on flux works as low as 6 GB GPUs
FYouTubeSECourses
If you want to train FLUX with maximum possible quality, this is the tutorial looking for. In this comprehensive tutorial, you will learn how to install Kohya GUI and use it to fully Fine-Tune / DreamBooth FLUX model. After that how to use SwarmUI to compare generated checkpoints / models and find the very best one to generate most amazing image...
Fyes which config you used?
Fand are your images all 1024x1024?
JYes. All images are 1024. The config is 24GB_GPU_22900MB_7.3_second_it_Tier_1.
Mentioning this because I think it's strange. I am noticing when I add the preset to kohya preset nothing changes. I have to go through and manually change everything. and when I save the config. It doesn't save. refreshing the browser will erase all data.
I have 200gb storage, 30 gb of local storage like you say in the video.
Mentioning this because I think it's strange. I am noticing when I add the preset to kohya preset nothing changes. I have to go through and manually change everything. and when I save the config. It doesn't save. refreshing the browser will erase all data.
I have 200gb storage, 30 gb of local storage like you say in the video.
Fthat means you didnt load config accurately
Fit has to load everything
Ftell me your config path you tried to load
JLet me check. this is also what I am running it on. pytorch:2.2.0-py3.10-cuda12.1.
JShould I make sure the folders don't have spaces in the names? I keep remembering runpod doesn't like spaces.
Fyes never use space anywhere
Frunpod starts with
F/workspace/ etc
J/workspace/dreambooth/DreamBooth_Tab_Fine_Tuning_Best_FLUX_Configs/24GB_GPU_22900MB_7.3_second_it_Tier_1.json
JIt looks like the config file path is ok.
Fyes you loaded into dreambooth tab
For lora tab
JCan I use flux1-dev-fp8.safetensors for training or do I need to use the original?
Fuse original
JIt was the dreambooth tab. I didn't use the original so I can try that out now.
Fye try it
JThat one strange thing is the config file isn't doing anyhting. very strange to me. It didn't save any of the work from before.
Fclick both
F
Fit has to load values
F
F
JIt seemed to have saved this time. What do I put if I only want to save the 160th epoch in the "Save every N epochs" .
Jthis is what the config file has loaded minus the save every n epoch number. I added 160.
Hamazing --- where are you doing full dreambooth? which script in kohya does that.... not seeing it in the video
Hthere doesn't seem to be any script in kohya that lets you do dreambooth with flux
JI went with the 16gb config file and its working. it looks like there was something that was causing it to fail at 24gb.
I don't know if this matters but I am getting this during the training. however this was also happening during the 16gb training too.
2025-03-22 02:58:21.761881: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
I don't know if this matters but I am getting this during the training. however this was also happening during the 16gb training too.
2025-03-22 02:58:21.761881: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
Hthis script will let you do full flux finetuning on low vram GPUs
https://github.com/kohya-ss/sd-scripts/blob/sd3/flux_train.py
but there is no script that does dreambooth training? so it seems like the video you posted is not using dreambooth -- please correct me if i am wrong
@Furkan Gözükara SECourses
https://github.com/kohya-ss/sd-scripts/blob/sd3/flux_train.py
but there is no script that does dreambooth training? so it seems like the video you posted is not using dreambooth -- please correct me if i am wrong
@Furkan Gözükara SECourses
GitHub
Contribute to kohya-ss/sd-scripts development by creating an account on GitHub.
Hunless this line implies using dreambooth: https://github.com/kohya-ss/sd-scripts/blob/sd3/flux_train.py#L88
GitHub
Contribute to kohya-ss/sd-scripts development by creating an account on GitHub.
H
WHi @Furkan Gözükara SECourses I just download your config for SDXL training. For training dreambooth for character how many regulation images from your database you think we need to use train to get good dreambooth character model
SHi @Furkan Gözükara SECourses , I've 33 images of me. can you suggest how many repeats I should consider(config has 40 repeats and 1 epoch, that gives 1320 steps).
Swhat model should I use for the best results sdxl base or any custom model from Civitai (like realvis). Is this the best method for generating images of a specific person?