Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: openrail++
|
5 |
+
thumbnail: "https://huggingface.co/nitrosocke/Ghibli-Diffusion/resolve/main/images/ghibli-diffusion-thumbnail.jpg"
|
6 |
+
tags:
|
7 |
+
- stable-diffusion
|
8 |
+
- text-to-image
|
9 |
+
- image-to-image
|
10 |
+
- diffusers
|
11 |
+
|
12 |
+
---
|
13 |
+
### Mad Max: Fury Road Diffusion (SD 2.0, 768x768)
|
14 |
+
|
15 |
+
This is the fine-tuned Stable Diffusion model trained on images from Mad Max: Fury Road.
|
16 |
+
Use the tokens **_mad_max_fr_** in your prompts for the effect.
|
17 |
+
|
18 |
+
|
19 |
+
**Images rendered with the model:**
|
20 |
+
Turn your favorite cars, city's, characters in fury road style.
|
21 |
+
|
22 |
+
![Samples](https://huggingface.co/valhalla/mad_max_diffusion-sd2/resolve/main/mad-max-fr.png)
|
23 |
+
|
24 |
+
|
25 |
+
### 🧨 Diffusers
|
26 |
+
|
27 |
+
This model can be used just like any other Stable Diffusion model. For more information,
|
28 |
+
please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
29 |
+
|
30 |
+
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]().
|
31 |
+
|
32 |
+
```python
|
33 |
+
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
|
34 |
+
import torch
|
35 |
+
model_id = "valhalla/mad_max_diffusion-sd2"
|
36 |
+
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda")
|
37 |
+
pipe.enable_attention_slicing()
|
38 |
+
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
|
39 |
+
|
40 |
+
prompt = "The streets of Paris with eiffel tower in the background in the style of mad_max_fr"
|
41 |
+
image = pipe(prompt, num_inference_steps=30).images[0]
|
42 |
+
image.save("./paris-mad-max-fr.png")
|
43 |
+
```
|