Evo-Ukiyoe-v1
Evo-Ukiyoe adapts EvoSDXL-JP with a trained LoRA for ukiyo-e imagery. Sakana used images from Ritsumeikan University's Art Research Center.
Research release
The LoRA learns a specific visual tradition
The repository provides its own loader and a Japanese prompting example. The training collection is credited to the Art Research Center rather than presented as Sakana-owned historical art.Evo-Ukiyoe-v1 official model card
Working with this release
Practical guidance. Describe the subject, clothing and setting directly. Inspect hands, written characters and historical objects before using an output in educational material.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | SakanaAI/Evo-Ukiyoe-v1 |
| Ancestry | EvoSDXL-JP-v1 plus Sakana's ukiyo-e LoRA.Evo-Ukiyoe-v1 official model card |
| Terms | Code and LoRA: Apache 2.0. The full pipeline retains upstream terms; described as an educational research prototype.Evo-Ukiyoe-v1 official model card |
Related models
- Evo-Nishikie-v1
Sakana AI · Evo-Ukiyoe
A ControlNet model trained with Evo-Ukiyoe to add color to ukiyo-e images.
Launch date not confirmedResearch releaseDownloadable - EvoSDXL-JP-v1
Sakana AI · EvoSDXL-JP
An SDXL image-generation model combining Japanese prompt understanding with SDXL-Lightning.
Launch date not confirmedResearch releaseDownloadable