Verified: a year ago
SafeTensor
Type | |
Stats | 2,229 45,214 |
Reviews | (183) |
Published | Oct 29, 2023 |
Base Model | |
Training | Epochs: 60 |
Usage Tips | Clip Skip: 1 |
Trigger Words | very dark focused flash photo |
Hash | AutoV2 C706E3F283 |
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.