vandergraf/DxD all girls + Gasper (Rias, Sona, Yasaka, Venelana, Akeno, Asia, Tsubaki, Xenovia, Grayfia, Kunou, Gasper, Rossweisse,
Hello, I trained this lora on AnythingV4.5 with screenshoots from anime and cards from mobile game. It was extremely hard to make all the characters turn out fine and there are no artifacts. So please share your results. For good result you should use upscaler. At frist I generated many arts without upscaler, then chose best, copyd they Seed and re-generated with upscaler(R-ESRGAN 4x+ with denoising=0.7). All images generated on AOM3, Starlike, jafamix with orangemix Vae. DPM++ 2m Karras 6-9 CFG 20-40 steps and 0.6-0.7 Lora weight For good Ophis you should download text inversion from Corneo.
| Author / organization | vandergraf |
|---|---|
| Downloads | 5.9K (as reported by Civitai) |
| Likes | 904 |
| Task | text-to-image |
| Created | 7 April 2023 |
| Last updated at source | — |
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.