Ellie_Williams/Underwater (Concept)
This LoRa is trained to produce underwater pictures . It was trained on 400+ manually selected and cropped pictures. It works best with 512x768 , 768x512 and 768x768 resolution. Note : if you want to try to create images in a swimming pool, do not use the tag "swimming pool" , use "floor tile" or "tile" instead (and/or "walls"). This is because your Checkpoint most likely associates "swimming pool" with surface pictures.
| Author / organization | Ellie_Williams |
|---|---|
| Downloads | 3.8K (as reported by Civitai) |
| Likes | 681 |
| Task | text-to-image |
| Created | 10 September 2023 |
| Last updated at source | — |
Popularity, last 3 days
3,756 now. Counts as reported by the source, snapshotted daily by Silytics.
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 Information may be incomplete or out of date.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.