Patreon
Home / Apps / Research, Comparisons and Experiments / FLUX De-Distilled Fine-Tuning & LoRA Tests: Bleeding and CFG

FLUX De-Distilled Fine-Tuning & LoRA Tests: Bleeding and CFG Results

FLUX de-distilled models train best at guidance scale 3.5 instead of 1, yet these DreamBooth and LoRA experiments show they still do not fix bleeding.

fine tuninglora trainingcomparison
FLUX De-Distilled Fine-Tuning & LoRA Tests: Bleeding and CFG Results

Highlights

Anti-bleeding tests train two people together on FLUX Dev, Verus Vision 1.0b, PixelWave v03 and FLUX Dev De-Distilled with 28-image datasets. Also tests the CFG impact for stylized images such as anime or paintings on regular FLUX Dev, where CFG 3.5 is worth testing.

What it tests

Experiments with de-distilled FLUX models for full fine-tuning / DreamBooth and LoRA training, based on our FLUX fine-tuning workflow (tutorial, configs post).

Key findings

Models tested

FLUX Dev, Verus Vision 1.0b, PixelWave v03 and FLUX Dev De-Distilled, trained with 28-image datasets and compared on full grids (dataset post).

Video tutorial

Train FLUX on Your Own Photos With Just a 6 GB GPU: Full Fine-Tuning Course (Kohya, 2024) · chapters and summary

Where to get it: the installers, presets and full instructions are in this Patreon post by Furkan Gözükara (SECourses). Published Oct 31, 2024.

Related

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.

FLUX 2 vs FLUX SRPO & New Kohya SS GUI Premium FLUX Training App

FLUX 2 vs FLUX SRPO & New Kohya SS GUI Premium FLUX Training App

FLUX 2 Pro compared with a trained FLUX SRPO model, plus the new Kohya trainer V35 that trains FLUX on GPUs with as little as 6 GB VRAM.

FLUX LoRA vs Fine Tuning / DreamBooth Comparison: Batch Size 1 vs 7

FLUX LoRA vs Fine Tuning / DreamBooth Comparison: Batch Size 1 vs 7

FLUX LoRA and Fine Tuning / DreamBooth compared with 15 and 256 training images at batch size 1 and 7, for both realism and stylization.

More in Research, Comparisons and Experiments.