adempotent/Flash Photo SDXL
1 MB iA3 Network *UPDATE *: v6 is trained with Debiased Estimation Loss on the dev branch of kohya_ss sd-scripts. This makes image structure more coherent and have better color. If you train a model with Debiased Estimation Loss, you shouldn't need to use Min-SNR gamma or Color Aug as it does both better. Prompt format: very dark focused flash photo of subject at night, wide angle, black background I recommend using DPM++ 3M Exponential/Karras with 40-100 steps. Use the refiner at 0.8 for photorealism.
| Author / organization | adempotent |
|---|---|
| Downloads | 4.3K (as reported by Civitai) |
| Likes | 389 |
| Task | text-to-image |
| Created | 29 October 2023 |
| Last updated at source | — |
More from adempotent
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 Information may be incomplete or out of date.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.