Instructions to use kandinsky-community/kandinsky-2-2-controlnet-depth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kandinsky-community/kandinsky-2-2-controlnet-depth with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kandinsky-community/kandinsky-2-2-controlnet-depth", 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 scheduler/scheduler_config.json
Browse files
scheduler/scheduler_config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
"beta_schedule": "linear",
|
| 6 |
"beta_start": 0.00085,
|
| 7 |
"beta_end":0.012,
|
| 8 |
-
"clip_sample" :
|
| 9 |
"set_alpha_to_one" : false,
|
| 10 |
"steps_offset" : 1,
|
| 11 |
"prediction_type" : "epsilon",
|
|
|
|
| 5 |
"beta_schedule": "linear",
|
| 6 |
"beta_start": 0.00085,
|
| 7 |
"beta_end":0.012,
|
| 8 |
+
"clip_sample" : true,
|
| 9 |
"set_alpha_to_one" : false,
|
| 10 |
"steps_offset" : 1,
|
| 11 |
"prediction_type" : "epsilon",
|