Patreon
Home / Apps / LoRA and Fine-Tuning Training: Kohya, Musubi Tuner, OneTrainer, AI Toolkit / FLUX LoRA Trained on 256 Images of Myself: Mind-Blowing Resu

FLUX LoRA Trained on 256 Images of Myself: Mind-Blowing Results

FLUX LoRA trained with Kohya GUI on 256 phone photos of myself, including the Clip-L and T5-XXL text encoders; it learned body shape and fine facial details.

lora trainingcomparisonswarmuiupscaling
FLUX LoRA Trained on 256 Images of Myself: Mind-Blowing Results

Highlights

Short conclusions: 256 images caused more overfitting than needed, so prompts had to describe backgrounds in more detail, yet outputs were more lively and realistic. Images were generated in SwarmUI and upscaled 2x with our SUPIR app; links lead to the full workflow, configs and tutorials.

Video tutorial

No Powerful GPU? Train a FLUX LoRA in the Cloud in Under 1 Hour (2024 Kohya Guide) · chapters and summary

More videos: Enhance Images Like in Sci-Fi Movies on an 8 GB GPU: SUPIR AI Upscaler Full Tutorial (2024), Train FLUX on Your Own Photos With Just 8GB VRAM: Kohya GUI LoRA Tutorial (2024, Windows)

Where to get it: the full post is free on this Patreon post by Furkan Gözükara (SECourses). Published Sep 14, 2024.

Related

Musubi Tuner App: 1-Click LoRA & Fine-Tune Training With 435 Presets

Musubi Tuner App: 1-Click LoRA & Fine-Tune Training With 435 Presets

SECourses Musubi Tuner trains LoRAs and full fine-tunes of Qwen Image, Wan 2.2, FLUX 2, Z Image and LTX 2.3 on Windows or cloud GPUs with 435 ready presets.

Kohya FLUX LoRA Training: Full Tutorial & Configs for Windows & Cloud

Kohya FLUX LoRA Training: Full Tutorial & Configs for Windows & Cloud

Kohya SS GUI FLUX LoRA training step by step, with the best optimized configs for 4 GB to 48 GB GPUs and a 68 minute Windows tutorial with 74 chapters.

Qwen Image 2512 Training Comparison: The Best Model to Train

Qwen Image 2512 Training Comparison: The Best Model to Train

Qwen Image 2512 is the new king for training: the video compares trained Base, 2512, Edit 2509 and Edit 2511 models and shows a big leap in realism.

More in LoRA and Fine-Tuning Training: Kohya, Musubi Tuner, OneTrainer, AI Toolkit.