---
license: creativeml-openrail-m
---

---
license: creativeml-openrail-m
---

This is a low-quality bocchi-the-rock (ぼっち・ざ・ろっく!) character model.
Similar to my [yama-no-susume model](https://huggingface.co/alea31415/yama-no-susume), this model is capable of generating **multi-character scenes** beyond images of a single character.
Of course, the result is still hit-or-miss, but I think the success rate of getting the **entire Kessoku Band** right in one shot is already quite high,
and otherwise, you can always rely on inpainting.
Here are two examples:

With inpainting
*Coming soon*

Without inpainting
*Coming soon*


### Characters

The model knows 12 characters from bocchi the rock.
The ressemblance with a character can be improved by a better description of their appearance.

*Coming soon*

### Dataset description

The dataset contains around 27K images with the following composition
- 7024 anime screenshots
- 1630 fan arts
- 18519 customized regularization images

The model is trained with a specific weighting scheme to balance between different concepts.
For example, the above three categories have weights respectively 0.3, 0.25, and 0.45.
Each category is itself split into many sub-categories in a hierarchical way.
For more details on the data preparation process please refer to https://github.com/cyber-meow/anime_screenshot_pipeline


### Training Details

#### Trainer
The model is trained using [EveryDream1](https://github.com/victorchall/EveryDream-trainer) as
EveryDream seems to be the only trainer out there that supports sample weighting (through the use of `multiply.txt`).
Note that for future training it makes sense to migrate to [EveryDream2](https://github.com/victorchall/EveryDream2trainer).

#### Hardware and cost
The model is trained on runpod using 3090 and cost me around 15 dollors.

#### Hyperparameter specification

- The model is trained for 48000 steps, at batch size 4, lr 1e-6, resolution 512, and conditional dropping rate of 10%.

Note that as a consequence of the weighting scheme which translates into a number of different multiply for each image,
the count of repeat and epoch has a quite different meaning here.
For example, depending on the weighting, I have around 300K images (some images are used multiple times) in an epoch,
and therefore I did not even finish an entire epoch with the 48000 steps at batch size 4.

### Failures

- For the first 24000 steps I use the trigger words `Bfan1` and `Bfan2` for the two fans of Bocchi.
  However, these two words are too similar and the model fails to different characters for these. Therefore I changed Bfan2 to Bofa2 at step 24000.


### More Example Generations

With inpainting
*Coming soon*

Without inpainting
*Coming soon*

Some failure cases
*Coming soon*