Day 2/7 of training some proper realism into this plastic AI world.
Trained on 97 frames of societies most beloved police interrogations as seen on the media.
milage may vary with this one.
trigger word: interrogationCam
strength: 1.8 and above gives the sweet grittiness you're searching for
reuploaded v1.01 with an exchanged sha256 hash. Seems like ortis' ai-Toolkit generates faulty hashes by generating it from an empty string. Every lora ends up with the same hash, breaking crossposting on civitai (https://github.com/ostris/ai-toolkit/issues/130)
Thanks to diogod for pointing this out! <3
This is the first version trained on the full dataset. No changes or imrpovements for now
1. Os direitos dos modelos repostados pertencem aos criadores originais.
2. Criadores originais que desejam reivindicar seus modelos devem contatar a equipe do SeaArt AI pelos canais oficiais. Clique para reivindicar
