Description
This LoRA trained using kohya_ss on 60 images 1024×1024 up to 12000 steps (50 epochs, 240 steps each) without captions and without regularization images.
Source model: ‘Source model: flux1-dev’. This LoRA would works well with flux1-dev and flux1-schnell. Also this LoRA should works well with most of community trained FLUX family checkpoints.
Learning rate: 0.00005.
Precision: fp16.
LR Scheduler: constant.
Below is example of testing AIDA_FXLR_ElonaV LoRA in Comfy_UI with flux1-dev:
Click on the image to view or download it in the original size.
Below is example of testing AIDA_FXLR_ElonaV LoRA in Comfy_UI with flux1-schnell:
Click on the image to view or download it in the original size.
Below is download link for Comfy_UI .json config to reproduce this workflow:
2024-12-04-032243_flux1-dev_1119332752928274.json_.zip
I packed it into .zip because my site can’t host .json files.
Download link to AIDA_FXLR_ElonaV.safetensors will be available for you after purchase. For your comfort I packed AIDA_FXLR_ElonaV.safetensors into .zip archive with AIDA_FXLR_ElonaV.png and AIDA_FXLR_ElonaV.txt. Preview and description are compatible with AUTOMATIC1111 and Forge extra networks tabs.
Purchasing this asset you will achieve rights for selling images generated with AIDA_FXLR_ElonaV.safetensors LoRA. If you want say special thanks to me, you can add additional amount to your payment.
Please contact me if you need some extended rights for sharing or selling AIDA_FXLR_ElonaV, merging AIDA_FXLR_ElonaV with other models, using AIDA_FXLR_ElonaV in generation services and so on.
Dom –
Looks like you’re missing Dominique Swain in this line up
AI Doll Agency –
Thank you for five stars. I can train a line of LoRAs on 17yo Dominique Swain as she was in 1997, or I can train on her character from Lolita movie. But highly likely it will be very costly due to low quality of source images. Please pay initial fee via commissions form and message me via email if you are serious.