Update README.md
Browse files
README.md
CHANGED
@@ -23,6 +23,9 @@ These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights
|
|
23 |
![img_1](./image_1.jpg)
|
24 |
![img_2](./image_2.jpg)
|
25 |
![img_3](./image_3.jpg)
|
|
|
|
|
|
|
26 |
|
27 |
|
28 |
|
@@ -31,12 +34,19 @@ These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights
|
|
31 |
#### How to use
|
32 |
|
33 |
```python
|
34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
```
|
36 |
|
37 |
#### Limitations and bias
|
38 |
-
|
39 |
-
[TODO: provide examples of latent issues and potential remediations]
|
40 |
|
41 |
## Training details
|
42 |
|
|
|
23 |
![img_1](./image_1.jpg)
|
24 |
![img_2](./image_2.jpg)
|
25 |
![img_3](./image_3.jpg)
|
26 |
+
![img_4](./image_0.png)
|
27 |
+
![img_5](./image_13.png)
|
28 |
+
![img_6](./image_17.png)
|
29 |
|
30 |
|
31 |
|
|
|
34 |
#### How to use
|
35 |
|
36 |
```python
|
37 |
+
from diffusers import AutoPipelineForText2Image
|
38 |
+
import torch
|
39 |
+
|
40 |
+
pipeline = AutoPipelineForText2Image.from_pretrained("runwayml/stable-diffusion-v1-5", torch_dtype=torch.float16, safety_checker=None).to("cuda")
|
41 |
+
pipeline.load_lora_weights("iamkaikai/MATISSEE-LORA", weight_name="pytorch_lora_weights.safetensors")
|
42 |
+
prompt = "MATISSEE-ART, brown, beige, coral, gray, orange red, violet, black, teal"
|
43 |
+
for i in range(20):
|
44 |
+
image = pipeline(prompt, num_inference_steps=20).images[0]
|
45 |
+
image.save(f"./image_{str(i)}.png")
|
46 |
```
|
47 |
|
48 |
#### Limitations and bias
|
49 |
+
For some reason, this LORA model will often trigger the NSFW filter. Make sure you turn it off in the pipeline.
|
|
|
50 |
|
51 |
## Training details
|
52 |
|