Instructions to use neuralvfx/LibreFlux-IP-Adapter-SAM-ControlNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use neuralvfx/LibreFlux-IP-Adapter-SAM-ControlNet with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("neuralvfx/LibreFlux-IP-Adapter-SAM-ControlNet", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -156,7 +156,7 @@ quantize(
|
|
| 156 |
)
|
| 157 |
|
| 158 |
quantize(
|
| 159 |
-
pipe.
|
| 160 |
weights=qint8,
|
| 161 |
exclude=[
|
| 162 |
"*.norm", "*.norm1", "*.norm2", "*.norm2_context",
|
|
@@ -166,7 +166,7 @@ quantize(
|
|
| 166 |
|
| 167 |
freeze(pipe.transformer)
|
| 168 |
freeze(pipe.ip_adapter)
|
| 169 |
-
freeze(pipe.
|
| 170 |
|
| 171 |
# Enable Model Offloading
|
| 172 |
pipe.enable_model_cpu_offload()
|
|
|
|
| 156 |
)
|
| 157 |
|
| 158 |
quantize(
|
| 159 |
+
pipe.controlnet,
|
| 160 |
weights=qint8,
|
| 161 |
exclude=[
|
| 162 |
"*.norm", "*.norm1", "*.norm2", "*.norm2_context",
|
|
|
|
| 166 |
|
| 167 |
freeze(pipe.transformer)
|
| 168 |
freeze(pipe.ip_adapter)
|
| 169 |
+
freeze(pipe.controlnet)
|
| 170 |
|
| 171 |
# Enable Model Offloading
|
| 172 |
pipe.enable_model_cpu_offload()
|