DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
About
The recent progress in text-to-image models pretrained on large-scale datasets has enabled us to generate various images as long as we provide a text prompt describing what we want. Nevertheless, the availability of these models is still limited when we expect to generate images that fall into a specific domain either hard to describe or just unseen to the models. In this work, we propose DomainGallery, a few-shot domain-driven image generation method which aims at finetuning pretrained Stable Diffusion on few-shot target datasets in an attribute-centric manner. Specifically, DomainGallery features prior attribute erasure, attribute disentanglement, regularization and enhancement. These techniques are tailored to few-shot domain-driven generation in order to solve key issues that previous works have failed to settle. Extensive experiments are given to validate the superior performance of DomainGallery on a variety of domain-driven generation scenarios. Codes are available at https://github.com/Ldhlwh/DomainGallery.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Few-shot Image Generation | Sunglasses 10-shot | FID43.1 | 36 | |
| Few-shot Image Generation | Babies 10-shot | FID58.86 | 35 | |
| Few-shot Image Generation | AFHQ-Dog 10-shot | FID123.5 | 34 | |
| Few-shot Image Generation | AFHQ-Wild 10-shot | FID65.32 | 34 | |
| Few-shot Image Generation | MetFaces 10-shot | FID60.38 | 34 | |
| Few-shot Image Generation | AFHQ-Cat 10-shot | FID77.15 | 34 | |
| Few-shot Image Generation | Sketches 10-shot | FID44.86 | 18 | |
| Intra-category image generation | CUFS sketches | FID44.86 | 4 | |
| Intra-category image generation | Van Gogh houses | KID32.2 | 4 | |
| Intra-category image generation | FFHQ sunglasses | FID43.1 | 4 |