Text-to-Image
Diffusers
Safetensors
English
NucleusMoEImagePipeline
Mixture of Experts
sparse-moe
diffusion
image-generation
Instructions to use NucleusAI/Nucleus-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use NucleusAI/Nucleus-Image with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("NucleusAI/Nucleus-Image", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Fix default guidance scale
#3
by sippycoder - opened
README.md
CHANGED
|
@@ -110,7 +110,7 @@ image = pipe(
|
|
| 110 |
width=width,
|
| 111 |
height=height,
|
| 112 |
num_inference_steps=50,
|
| 113 |
-
guidance_scale=
|
| 114 |
generator=torch.Generator(device="cuda").manual_seed(42),
|
| 115 |
).images[0]
|
| 116 |
|
|
|
|
| 110 |
width=width,
|
| 111 |
height=height,
|
| 112 |
num_inference_steps=50,
|
| 113 |
+
guidance_scale=4.0,
|
| 114 |
generator=torch.Generator(device="cuda").manual_seed(42),
|
| 115 |
).images[0]
|
| 116 |
|