Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,76 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## LORA Qwen-Image example
|
2 |
+
|
3 |
+
World first lora for [Qwen-Image](https://huggingface.co/Qwen/Qwen-Image)
|
4 |
+
|
5 |
+
No trigger word required
|
6 |
+
|
7 |
+
## 🧪 Usage
|
8 |
+
---
|
9 |
+
### 🔧 Initialization
|
10 |
+
|
11 |
+
```python
|
12 |
+
from diffusers import DiffusionPipeline
|
13 |
+
import torch
|
14 |
+
|
15 |
+
model_name = "Qwen/Qwen-Image"
|
16 |
+
|
17 |
+
# Load the pipeline
|
18 |
+
if torch.cuda.is_available():
|
19 |
+
torch_dtype = torch.bfloat16
|
20 |
+
device = "cuda"
|
21 |
+
else:
|
22 |
+
torch_dtype = torch.float32
|
23 |
+
device = "cpu"
|
24 |
+
|
25 |
+
pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype)
|
26 |
+
pipe = pipe.to(device)
|
27 |
+
```
|
28 |
+
|
29 |
+
### 🔌 Load LoRA Weights
|
30 |
+
|
31 |
+
```python
|
32 |
+
# Load LoRA weights
|
33 |
+
pipe.load_lora_weights('pytorch_lora_weights.safetensors', adapter_name="lora")
|
34 |
+
```
|
35 |
+
|
36 |
+
### 🎨 Generate Image with lora trained on person
|
37 |
+
|
38 |
+
```python
|
39 |
+
prompt = '''Super Realism portrait of a teenager woman of African descent, serene calmness, arms crossed, illuminated by dramatic studio lighting, sunlit park in the background, adorned with delicate jewelry, three-quarter view, sun-kissed skin with natural imperfections, loose shoulder-length curls, slightly squinting eyes, environmental street portrait with text "FLYMY AI" on t-shirt.'''
|
40 |
+
negative_prompt = " "
|
41 |
+
image = pipe(
|
42 |
+
prompt=prompt,
|
43 |
+
negative_prompt=negative_prompt,
|
44 |
+
width=1024,
|
45 |
+
height=1024,
|
46 |
+
num_inference_steps=50,
|
47 |
+
true_cfg_scale=5,
|
48 |
+
generator=torch.Generator(device="cuda").manual_seed(346346)
|
49 |
+
)
|
50 |
+
|
51 |
+
# Display the image (in Jupyter or save to file)
|
52 |
+
image.show()
|
53 |
+
# or
|
54 |
+
image.save("output.png")
|
55 |
+
```
|
56 |
+
|
57 |
+
### 🖼️ Sample Output
|
58 |
+
|
59 |
+

|
60 |
+
|
61 |
+
|
62 |
+
## 🤝 Support
|
63 |
+
|
64 |
+
If you have questions or suggestions, join our community:
|
65 |
+
- 🌐 [FlyMy.AI](https://flymy.ai)
|
66 |
+
- 💬 [Discord Community](https://discord.com/invite/t6hPBpSebw)
|
67 |
+
- 🐦 [Follow us on X](https://x.com/flymyai)
|
68 |
+
- 💼 [Connect on LinkedIn](https://linkedin.com/company/flymyai)
|
69 |
+
- 📧 [Support](mailto:[email protected])
|
70 |
+
|
71 |
+
**⭐ Don't forget to star the repository if you like it!**
|
72 |
+
|
73 |
+
|
74 |
+
---
|
75 |
+
license: apache-2.0
|
76 |
+
---
|