Japanese Stable Diffusion XL
Japanese Stable Diffusion XL adapts SDXL 1.0 for Japanese prompts and cultural concepts. It uses a Japanese-compatible text encoder with parameter-efficient adaptation.
Model design and access
The model aims to improve Japanese-language and cultural understanding while retaining the base model's visual range. The card warns that legible text, difficult object relationships and faces remain limitations. Understanding a Japanese prompt does not mean that the model reliably prints Japanese text inside an image.Japanese Stable Diffusion XL official model documentation
Practical use
Practical guidance. Use this release when the prompt's Japanese wording or cultural detail matters to the image. Evaluate with native-language descriptions and reference subjects rather than translated English benchmarks alone. Keep the intended visual style separate from the language of the prompt, and inspect any generated signage manually.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | JSDXL |
| Ancestry | Stable Diffusion XL 1.0.Japanese Stable Diffusion XL official model documentation |
| Adaptation | Orthogonal Fine-tuning with a Japanese-specific text encoder.Japanese Stable Diffusion XL official model documentation |
| License | Stability AI Community License.Japanese Stable Diffusion XL official model documentation |
Related models
- Stable Diffusion XL 1.0
Stability AI · Stable Diffusion
SDXL 1.0 is a latent-diffusion image model that can run as a standalone base or with a separate refiner.
Launch date not confirmedAPI · Downloadable