|
--- |
|
license: openrail++ |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
--- |
|
|
|
This is a copy of the SSD-1B model (https://huggingface.co/segmind/SSD-1B) with the unet replaced |
|
with the LCM distilled unet (https://huggingface.co/latent-consistency/lcm-ssd-1b) and scheduler config set to default to the LCM Scheduler. |
|
|
|
This makes LCM SSD-1B run as a standard Diffusion Pipeline |
|
|
|
```py |
|
from diffusers import DiffusionPipeline |
|
import torch |
|
|
|
pipe = DiffusionPipeline.from_pretrained( |
|
"Vargol/lcm-ssd-1b-full-model", variant='fp16', torch_dtype=torch.float16 |
|
).to("mps") |
|
|
|
prompt = "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k" |
|
generator = torch.manual_seed(0) |
|
|
|
image = pipe( |
|
prompt=prompt, num_inference_steps=4, generator=generator, guidance_scale=8.0 |
|
).images[0] |
|
|
|
image.save('distilled.png') |
|
|
|
``` |
|
|
