| license: other | |
| tags: | |
| - aesthetic | |
| - anime | |
| - detail | |
| - style | |
| # Anima RL - v0.1 - 2901967 | |
| **Model Type**: LORA | |
| **Base Model**: Anima | |
| **Trigger Words**: None | |
| **Tags**: aesthetic, anime, detail, style | |
| ## Gallery | |
| <table> | |
| <tr> | |
| <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/f47bba0c-6292-40b5-a0a1-78fac8207dbc/original=true/128948641.jpeg" width="200"></td> | |
| <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ded24429-1914-41ee-a3f4-b1645c2d7099/original=true/128948640.jpeg" width="200"></td> | |
| <td><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7cfc8f46-7873-4d0a-ad0f-13d6dae215a0/original=true/128948643.jpeg" width="200"></td> | |
| </tr> | |
| </table> | |
| ## Description | |
| This LoRA primarily enhances aesthetics and details. It is the result of a reinforcement learning (RL) experiment with a custom reward model, that went surprisingly well so I'm releasing it as a prototype. Trained on preview3. Paired images are base (left) vs LoRA (right). | |
| Use at weight 1 by default. Adjust weight up or down according to your preferences. Might need to raise the weight a bit above 1 when used with other checkpoints (it gets weakened when applied to a strong aesthetics finetune). | |
| --- | |
| Author: [circlestone_labs](https://civitai.com/user/circlestone_labs) | |
| Model: [CivitAI Model Page](https://civitai.com/models/2583128?modelVersionId=2901967) | |
| Archive: [CivArchive Page](https://civarchive.com/models/2583128?modelVersionId=2901967) | |
| <!-- Version: 20260601_upload --> |