|
--- |
|
license: creativeml-openrail-m |
|
--- |
|
# Arcane Diffusion |
|
This is the fine-tuned Stable Diffusion model trained on images from the TV Show Arcane. |
|
Use the tokens **_arcane style_** in your prompts for the effect. |
|
|
|
**If you enjoy my work, please consider supporting me** |
|
[](https://patreon.com/user?u=79196446) |
|
|
|
### 🧨 Diffusers |
|
|
|
This model can be used just like any other Stable Diffusion model. For more information, |
|
please have a look at the [Stable Diffusion](https://huggingface.co./docs/diffusers/api/pipelines/stable_diffusion). |
|
|
|
You can also export the model to [ONNX](https://huggingface.co./docs/diffusers/optimization/onnx), [MPS](https://huggingface.co./docs/diffusers/optimization/mps) and/or [FLAX/JAX](). |
|
|
|
```python |
|
#!pip install diffusers transformers scipy torch |
|
from diffusers import StableDiffusionPipeline |
|
import torch |
|
|
|
model_id = "nitrosocke/Arcane-Diffusion" |
|
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16) |
|
pipe = pipe.to("cuda") |
|
|
|
prompt = "arcane style, a magical princess with golden hair" |
|
image = pipe(prompt).images[0] |
|
|
|
image.save("./magical_princess.png") |
|
``` |
|
|
|
# Gradio & Colab |
|
|
|
We also support a [Gradio](https://github.com/gradio-app/gradio) Web UI and Colab with Diffusers to run fine-tuned Stable Diffusion models: |
|
[](https://huggingface.co./spaces/anzorq/finetuned_diffusion) |
|
[](https://colab.research.google.com/drive/1j5YvfMZoGdDGdj3O3xRU1m4ujKYsElZO?usp=sharing) |
|
|
|
 |
|
|
|
### Sample images from v3: |
|
 |
|
 |
|
### Sample images from the model: |
|
 |
|
### Sample images used for training: |
|
 |
|
|
|
**Version 3** (arcane-diffusion-v3): This version uses the new _train-text-encoder_ setting and improves the quality and edibility of the model immensely. Trained on 95 images from the show in 8000 steps. |
|
|
|
**Version 2** (arcane-diffusion-v2): This uses the diffusers based dreambooth training and prior-preservation loss is way more effective. The diffusers where then converted with a script to a ckpt file in order to work with automatics repo. |
|
Training was done with 5k steps for a direct comparison to v1 and results show that it needs more steps for a more prominent result. Version 3 will be tested with 11k steps. |
|
|
|
**Version 1** (arcane-diffusion-5k): This model was trained using _Unfrozen Model Textual Inversion_ utilizing the _Training with prior-preservation loss_ methods. There is still a slight shift towards the style, while not using the arcane token. |
|
|
