Sakana AIEvoSDXL-JP
EvoSDXL-JP-v1
EvoSDXL-JP-v1 merges Japanese prompt understanding with SDXL image-generation components and SDXL-Lightning.
Research release
Code licensing does not replace model terms
The repository supplies a loader that assembles the pipeline. Its Apache label applies explicitly to the Python script. The card separately warns that the combined model retains its ancestors' terms.EvoSDXL-JP-v1 official model card
Working with this release
Practical guidance. Keep the full component list with a deployment. Review Japanese text rendering separately from the overall image composition.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | SakanaAI/EvoSDXL-JP-v1 |
| Ancestry | SDXL, Juggernaut-XL-v9, SDXL-DPO, Japanese SDXL and SDXL-Lightning.EvoSDXL-JP-v1 official model card |
| Terms | Python code: Apache 2.0. The generated pipeline inherits the source-model licenses; research prototype.EvoSDXL-JP-v1 official model card |
Related models
- Evo-Ukiyoe-v1
Sakana AI ยท Evo-Ukiyoe
An EvoSDXL-JP adaptation with a trained LoRA for Japanese woodblock-print imagery.
Launch date not confirmedResearch releaseDownloadable