README.md

---
license: creativeml-openrail-m
---
**Mo Di Diffusion**

This is the fine-tuned Stable Diffusion model trained on screenshots from the modern age Disney movies.
Use the tokens **_modern disney style_** in your prompts for the effect.

If you enjoy this model, please check out my other models on [Huggingface](https://huggingface.co/nitrosocke)

**Videogame Characters rendered with the model:**
![Videogame Samples](https://huggingface.co/nitrosocke/mo-di-diffusion/resolve/main/modern-disfusion-samples-01s.jpg)
**Animal Characters rendered with the model:**
![Animal Samples](https://huggingface.co/nitrosocke/mo-di-diffusion/resolve/main/modern-disfusion-samples-02s.jpg)
**Cars and Landscapes rendered with the model:**
![Misc. Samples](https://huggingface.co/nitrosocke/mo-di-diffusion/resolve/main/modern-disfusion-samples-03s.jpg)

### 🧨 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
from diffusers import StableDiffusionPipeline
import torch

model_id = "nitrosocke/mo-di-diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "a magical princess with golden hair, modern disney style"
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:
[![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](https://huggingface.co/spaces/anzorq/finetuned_diffusion)
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1j5YvfMZoGdDGdj3O3xRU1m4ujKYsElZO?usp=sharing)

#### Prompt and settings for Lara Croft:
**modern disney lara croft**
_Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 3940025417, Size: 512x768_

#### Prompt and settings for Simba:
**modern disney (baby simba) Negative prompt: person human**
_Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 1355059992, Size: 512x512_

This model was trained using the diffusers based dreambooth training and prior-preservation loss in 9.000 steps and using the _train-text-encoder_ feature.