Ray3780/Z-Image-Aesthetic(Base & Turbo)
Z-Image Lora training test, Used for Z-Image aesthetic enhancement, improving illustration and artistic concepts. Z image turbo v1: Recommended settings: heunpp2 + linear_quadratic, cfg: 1.5, step: 20, 0.8-1.2 Z image Base v1: euler_ancesral + beta，30 step，4 cfg，0.6-1 weight Try it online: Tensor | Seaart | Liblib Z image turbo v1: The LoRa dataset uses a variety of training sets, which affects various styles, including realism, illustration, and animation. It also fixes the aesthetic issues of Z-image. Because LoRa training disrupts the acceleration effect, it requires 20 steps and cfg 1.5-2.
| Author / organization | Ray3780 |
|---|---|
| Downloads | 4.5K (as reported by Civitai) |
| Likes | 270 |
| Task | text-to-image |
| Created | 27 January 2026 |
| Last updated at source | — |
Popularity, last 3 days
4,481 now (+12 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from Ray3780
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.