Experimenting With OneTrainer — OneTrainer vs Kohya — Realism vs Stylization — Reg images vs No-Reg images

Experimenting With OneTrainer — OneTrainer vs Kohya — Realism vs Stylization — Reg images vs No-Reg images

I feel like reg images using in OneTrainer improved realism and also lessened the overfitting as expected

OneTrainer realism looks better than Kohya meanwhile Kohya generalization looks better

Download attached images to see full resolution

OneTrainer Stable Diffusion XL (SDXL) Fine Tuning Best Presets

Massive 4K Resolution Woman & Man Class Ground Truth Stable Diffusion Regularization Images Dataset

The Very Best Workflow For SDXL DreamBooth / Full Fine Tuning — Results Of 100+ Full Trainings

full res 1 : https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/MFi59IKvsMwv-JgMxd28I.jpeg

full res 2 : https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/WrGkxTYOarDf8B3CrxTgO.jpeg

full res 3 : https://cdn-uploads.huggingface.co/production/uploads/6345bd89fe134dfd7a0dba40/3gecfhhaXIgQDMIUDf9Bo.jpeg

--

--

Furkan Gözükara - PhD Computer Engineer, SECourses

Content producer of YouTube.com/SECourses : Stable Diffusion, Kohya LoRA, DreamBooth, Fine Tuning, SDXL, Automatic1111 Web UI, LLMs, GPT, TTS