Instructions to use Johnhex/Clam with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Johnhex/Clam with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Johnhex/Clam", 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
- Draw Things
- DiffusionBee
modify any configs
Browse files
scheduler/scheduler_config.json
CHANGED
|
@@ -8,7 +8,7 @@
|
|
| 8 |
"clip_sample_range": 1.0,
|
| 9 |
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
"num_train_timesteps": 1000,
|
| 11 |
-
"prediction_type": "
|
| 12 |
"sample_max_value": 1.0,
|
| 13 |
"set_alpha_to_one": false,
|
| 14 |
"steps_offset": 1,
|
|
|
|
| 8 |
"clip_sample_range": 1.0,
|
| 9 |
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
"num_train_timesteps": 1000,
|
| 11 |
+
"prediction_type": "epsilon",
|
| 12 |
"sample_max_value": 1.0,
|
| 13 |
"set_alpha_to_one": false,
|
| 14 |
"steps_offset": 1,
|
unet/diffusion_pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3438366373
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:841598c86049f082a12455ff51b5afb1524165b19fa29e1a0ede91d026a91d7e
|
| 3 |
size 3438366373
|