|
--- |
|
library_name: diffusers |
|
--- |
|
dreamboothed [stable diffusion 1.5](https://huggingface.co/runwayml/stable-diffusion-v1-5) to include the concept of `_alex_ person` based on 4 photos shared in the Intel Insiders Discord. |
|
published with permission. |
|
|
|
Usage example |
|
```python |
|
from diffusers import StableDiffusionPipeline |
|
|
|
model_cp = "Vipitis/SD-15-dreamed-alex-person" |
|
pipe = StableDiffusionPipeline.from_pretrained(model_cp) |
|
out = pipe(prompt="photo of _alex_ person", negative_prompt="additional fingers, jepg artefacts", num_inference_steps=35, guidance_scale=8.5) |
|
|
|
out.images[0] |
|
``` |
|
|
|
Running on Intel Arc (via optimum-intel), has to convert and compile the model on first attempt. |
|
```python |
|
from optimum.intel.openvino import OVStableDiffusionPipeline |
|
|
|
model_cp = "Vipitis/SD-15-dreamed-alex-person" |
|
ov_pipe = OVStableDiffusionPipeline.from_pretrained(model_cp, export=True, device="GPU") |
|
out = ov_pipe(prompt="photo of _alex_ person", negative_prompt="additional fingers, jepg artefacts", num_inference_steps=35, guidance_scale=8.5) |
|
|
|
out.images[0] |
|
``` |
