Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- text-to-image
|
4 |
+
- stable-diffusion
|
5 |
+
- diffusers
|
6 |
+
- image-generation
|
7 |
+
- flux
|
8 |
+
- safetensors
|
9 |
+
base_model: black-forest-labs/FLUX.1-dev
|
10 |
+
instance_prompt: cinematic_1940s
|
11 |
+
license: other
|
12 |
+
license_name: flux-1-dev-non-commercial-license
|
13 |
+
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
|
14 |
+
language:
|
15 |
+
- en
|
16 |
+
library_name: diffusers
|
17 |
+
---
|
18 |
+
# Cinematic-1940s
|
19 |
+
|
20 |
+
<div class="container">
|
21 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/652c2a63d78452c4742cd3d3/GZInT9JHrvs5iwWOSTz-A.png" width="1024"/>
|
22 |
+
</div>
|
23 |
+
|
24 |
+
Cinematic-1940s is a LoRA model finetuned to capture the essence of 1940s cinema, specifically designed to enhance the vintage film texture. It embodies a monochrome, high-contrast color palette reminiscent of classic film noir, which is particularly evident in its portrayal of characters (with a subtle bias towards the charismatic charm of the era), bustling cityscapes, and dramatic shadows. The model delivers an exceptional aesthetic experience, capturing the essence of a bygone era with modern precision.
|
25 |
+
|
26 |
+
<div class="container">
|
27 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/652c2a63d78452c4742cd3d3/jwvBnI0R3zVf3E0MN-frq.png" width="1024"/>
|
28 |
+
</div>
|
29 |
+
|
30 |
+
|
31 |
+
## Trigger words
|
32 |
+
|
33 |
+
You should use `cinematic_1940s` to trigger the image generation.
|
34 |
+
|
35 |
+
|
36 |
+
## Inference
|
37 |
+
|
38 |
+
```python
|
39 |
+
import torch
|
40 |
+
from diffusers import FluxPipeline
|
41 |
+
|
42 |
+
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
|
43 |
+
pipe.load_lora_weights('aixonlab/Cinematic-1940s', weight_name='cinematic-1940s.safetensors')
|
44 |
+
pipe.fuse_lora(lora_scale=0.8)
|
45 |
+
pipe.to("cuda")
|
46 |
+
|
47 |
+
prompt = "a gorgeous woman and a man, cinematic_1940s"
|
48 |
+
|
49 |
+
image = pipe(prompt,
|
50 |
+
num_inference_steps=24,
|
51 |
+
guidance_scale=3.0,
|
52 |
+
width=768, height=1024,
|
53 |
+
).images[0]
|
54 |
+
image.save(f"example.png")
|
55 |
+
```
|
56 |
+
|
57 |
+
|
58 |
+
## Acknowledgements
|
59 |
+
This model is trained by AIXON Lab. We release this model under permissions. The model follows [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
|