Fireworks RFT now available! Fine-tune open models that outperform frontier models. Try today

Model Library/Stability/Japanese Stable Diffusion XL
Stability Logo Mark

Japanese Stable Diffusion XL

Ready
Try in Playground
fireworks/japanese-stable-diffusion-xl

    Japanese Stable Diffusion XL (JSDXL) is a Japanese-specific SDXL model that is capable of inputting prompts in Japanese and generating Japanese-style images.

    Japanese Stable Diffusion XL API Features

    Serverless

    Docs

    Immediately run model on pre-configured GPUs and pay-per-token

    On-demand Deployment

    Docs

    On-demand deployments give you dedicated GPUs for Japanese Stable Diffusion XL using Fireworks' reliable, high-performance system with no rate limits.

    Available Serverless

    Run queries immediately, pay only for usage

    $0.00
    Per 1K Tokens

    Japanese Stable Diffusion XL FAQs

    What is Japanese Stable Diffusion XL and who developed it?

    Japanese Stable Diffusion XL (JSDXL) is a Japanese-specific fine-tuned version of Stable Diffusion XL (SDXL 1.0), developed by Stability AI. It is optimized for understanding and generating Japanese-style images from Japanese-language prompts. The model uses Orthogonal Fine-tuning (OFT) and a custom Japanese-compatible text encoder for improved cultural and linguistic alignment.

    What applications and use cases does Japanese Stable Diffusion XL excel at?
    • Japanese prompt-to-image generation
    • Japanese anime-style, landscape, and artistic illustration
    • Cultural concept expression (e.g., ukiyo-e, samurai, traditional attire)
    • Educational or creative tools targeting Japanese language users
    • Design and visual art creation
    What are known failure modes of Japanese Stable Diffusion XL?
    • Cannot render legible text in generated images
    • Fails at compositional tasks (e.g., “a red cube on a blue sphere”)
    • Does not achieve perfect photorealism
    • Faces and people may be distorted
    • Model may reinforce social or cultural biases
    What rate limits apply on the shared endpoint?
    • Serverless: Supported
    • On-demand: Supported with no rate limits on dedicated GPU infrastructure
    What license governs commercial use of Japanese Stable Diffusion XL?

    The model is released under the Stability AI Community License. For commercial use, refer to https://stability.ai/license.

    Metadata

    State
    Ready
    Created on
    N/A
    Kind
    Base model
    Provider
    Stability
    Hugging Face
    japanese-stable-diffusion-xl

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    N/A

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Supported
    Serverless LoRA
    Not supported
    Context Length
    N/A
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported