ReGain: Restoring Subject Fidelity in Personalization on Synthetic Images
Quick summary
arXiv:2609.38680v1 Announce Type: cross Abstract: Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images. Increasingly, these images come from a diffusion model rather than a camera. We show that fine-tuning on such synthetic images degrades subject fidelity, producing oversaturated color and excess high-frequency detail. To isolate the cause, we fine-tune two models from the same base model with the same DreamBooth recipe, one on real photos of a subject and one on synthetic images of that subject generated by the first. We trace the
Key takeaways
- arXiv:2609.38680v1 Announce Type: cross Abstract: Text-to-image diffusion models are personalized to a subject by DreamBooth fine-tuning on a handful of its images.
- Increasingly, these images come from a diffusion model rather than a camera.
- We show that fine-tuning on such synthetic images degrades subject fidelity, producing oversaturated color and excess high-frequency detail.
Why it matters
This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.
Member comments