Instructions to use dg845/diffusers-cm_edm_imagenet64_ema with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use dg845/diffusers-cm_edm_imagenet64_ema with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("dg845/diffusers-cm_edm_imagenet64_ema", 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
Upload scheduler_config.json
Browse filesFix scheduler (use precondition_type "cm_edm" instead of "edm").
scheduler/scheduler_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"clip_sample": false,
|
| 5 |
"clip_sample_range": 1.0,
|
| 6 |
"num_train_timesteps": 40,
|
| 7 |
-
"precondition_type": "
|
| 8 |
"prediction_type": "sample",
|
| 9 |
"rho": 7.0,
|
| 10 |
"s_churn": 0.0,
|
|
|
|
| 4 |
"clip_sample": false,
|
| 5 |
"clip_sample_range": 1.0,
|
| 6 |
"num_train_timesteps": 40,
|
| 7 |
+
"precondition_type": "cm_edm",
|
| 8 |
"prediction_type": "sample",
|
| 9 |
"rho": 7.0,
|
| 10 |
"s_churn": 0.0,
|