Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -37,24 +37,22 @@ This model is designed for:
|
|
37 |
- Corporate branding and marketing content creation
|
38 |
- Research into personalized diffusion models
|
39 |
|
40 |
-
##
|
41 |
-
|
42 |
-
### Basic Usage
|
43 |
|
44 |
```python
|
45 |
-
from diffusers import StableDiffusion3Pipeline
|
46 |
import torch
|
|
|
47 |
|
48 |
-
|
49 |
-
pipe = StableDiffusion3Pipeline.from_pretrained(
|
50 |
"cfchase/redhat-dog-sd3",
|
51 |
-
torch_dtype=torch.
|
52 |
)
|
53 |
-
|
|
|
|
|
54 |
|
55 |
# Generate an image
|
56 |
-
|
57 |
-
image = pipe(prompt).images[0]
|
58 |
image.save("redhat_dog_park.png")
|
59 |
```
|
60 |
|
@@ -112,14 +110,6 @@ The training data consists of approximately 5-10 high-quality images of the Red
|
|
112 |
- Professional photography quality
|
113 |
- Clear subject focus
|
114 |
|
115 |
-
## Ethical Considerations
|
116 |
-
|
117 |
-
This model is intended for educational and corporate branding purposes. Users should:
|
118 |
-
- Respect Red Hat's trademark and branding guidelines
|
119 |
-
- Avoid generating misleading or inappropriate content
|
120 |
-
- Consider the environmental impact of inference computations
|
121 |
-
- Use responsibly in accordance with AI ethics best practices
|
122 |
-
|
123 |
## Technical Specifications
|
124 |
|
125 |
- **Model Size**: ~47GB (full precision weights)
|
@@ -130,20 +120,6 @@ This model is intended for educational and corporate branding purposes. Users sh
|
|
130 |
- PyTorch 2.0+
|
131 |
- Diffusers library
|
132 |
|
133 |
-
## Citation
|
134 |
-
|
135 |
-
If you use this model in your research or applications, please cite:
|
136 |
-
|
137 |
-
```bibtex
|
138 |
-
@misc{redhat-dog-sd3,
|
139 |
-
title={RedHat Dog SD3: Fine-tuned Stable Diffusion 3.5 for Corporate Branding},
|
140 |
-
author={Red Hat AI},
|
141 |
-
year={2025},
|
142 |
-
howpublished={Hugging Face Model Hub},
|
143 |
-
url={https://huggingface.co/cfchase/redhat-dog-sd3}
|
144 |
-
}
|
145 |
-
```
|
146 |
-
|
147 |
## License
|
148 |
|
149 |
This model is based on Stable Diffusion 3.5 Medium and is subject to the same licensing terms. Please refer to the [original model license](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium) for details.
|
|
|
37 |
- Corporate branding and marketing content creation
|
38 |
- Research into personalized diffusion models
|
39 |
|
40 |
+
## Example
|
|
|
|
|
41 |
|
42 |
```python
|
|
|
43 |
import torch
|
44 |
+
from diffusers import DiffusionPipeline
|
45 |
|
46 |
+
pipeline = DiffusionPipeline.from_pretrained(
|
|
|
47 |
"cfchase/redhat-dog-sd3",
|
48 |
+
torch_dtype=torch.bfloat16
|
49 |
)
|
50 |
+
|
51 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
52 |
+
pipeline.to(device)
|
53 |
|
54 |
# Generate an image
|
55 |
+
image = pipeline("photo of a rhteddy dog in a park").images[0]
|
|
|
56 |
image.save("redhat_dog_park.png")
|
57 |
```
|
58 |
|
|
|
110 |
- Professional photography quality
|
111 |
- Clear subject focus
|
112 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
113 |
## Technical Specifications
|
114 |
|
115 |
- **Model Size**: ~47GB (full precision weights)
|
|
|
120 |
- PyTorch 2.0+
|
121 |
- Diffusers library
|
122 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
## License
|
124 |
|
125 |
This model is based on Stable Diffusion 3.5 Medium and is subject to the same licensing terms. Please refer to the [original model license](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium) for details.
|