wanghaofan
commited on
Commit
•
77ff92b
1
Parent(s):
8aa998b
Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,9 @@ tags:
|
|
4 |
- stable-diffusion
|
5 |
- lora
|
6 |
- diffusers
|
7 |
-
-
|
|
|
|
|
8 |
widget:
|
9 |
- text: logo,Minimalist,Make a picture of a camera with the word 'Me'
|
10 |
output:
|
@@ -23,20 +25,42 @@ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICE
|
|
23 |
---
|
24 |
# FLUX.1-dev-LoRA-Logo-Design
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
<Gallery />
|
27 |
|
28 |
|
29 |
## Trigger words
|
30 |
|
31 |
-
You should use `wablogo`
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
|
33 |
-
|
|
|
|
|
|
|
34 |
|
35 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
|
|
|
37 |
|
38 |
-
|
39 |
|
40 |
-
Weights for this model are available in Safetensors format.
|
41 |
|
42 |
-
|
|
|
|
4 |
- stable-diffusion
|
5 |
- lora
|
6 |
- diffusers
|
7 |
+
- image-generation
|
8 |
+
- flux
|
9 |
+
- safetensors
|
10 |
widget:
|
11 |
- text: logo,Minimalist,Make a picture of a camera with the word 'Me'
|
12 |
output:
|
|
|
25 |
---
|
26 |
# FLUX.1-dev-LoRA-Logo-Design
|
27 |
|
28 |
+
This is a LoRA (Logo-Design) trained on FLUX.1-dev by [CJim](https://www.shakker.ai/userpage/b43e5cc7fcd64d2bbde42c6e889267cc/publish) on [Shakker AI](https://www.shakker.ai/modelinfo/0355942f9bd140a99e371ba5731894e8?from=personal_page).
|
29 |
+
<div class="container">
|
30 |
+
<img src="./poster.jpg" width="1024"/>
|
31 |
+
</div>
|
32 |
+
|
33 |
+
## Showcases
|
34 |
<Gallery />
|
35 |
|
36 |
|
37 |
## Trigger words
|
38 |
|
39 |
+
You should use `wablogo, logo, Minimalist` as trigger words. The recommended scale is `0.8` in diffusers.
|
40 |
+
|
41 |
+
## Inference
|
42 |
+
|
43 |
+
```python
|
44 |
+
import torch
|
45 |
+
from diffusers import FluxPipeline
|
46 |
|
47 |
+
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
|
48 |
+
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-Logo-Design", weight_name="FLUX-dev-lora-Logo-Design.safetensors")
|
49 |
+
pipe.fuse_lora(lora_scale=0.8)
|
50 |
+
pipe.to("cuda")
|
51 |
|
52 |
+
prompt = "logo,Minimalist,A bunch of grapes and a wine glass"
|
53 |
+
image = pipe(prompt,
|
54 |
+
num_inference_steps=24,
|
55 |
+
guidance_scale=3.5,
|
56 |
+
).images[0]
|
57 |
+
image.save(f"example.png")
|
58 |
+
```
|
59 |
|
60 |
+
## Online Inference
|
61 |
|
62 |
+
You can also download this model at [Shakker AI](https://www.shakker.ai/modelinfo/0355942f9bd140a99e371ba5731894e8?from=personal_page), where we provide an online interface to generate images.
|
63 |
|
|
|
64 |
|
65 |
+
## Acknowledgements
|
66 |
+
This model is trained by our copyrighted users [CJim](https://www.shakker.ai/userpage/b43e5cc7fcd64d2bbde42c6e889267cc/publish). 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).
|