Commit
•
0edee8c
1
Parent(s):
c091317
Update README.md
Browse files
README.md
CHANGED
@@ -3,8 +3,11 @@ license: mit
|
|
3 |
tags:
|
4 |
- generative model
|
5 |
- unconditional image generation
|
6 |
-
|
7 |
---
|
|
|
|
|
|
|
8 |
Consistency models are a new class of generative models introduced in ["Consistency Models"](https://arxiv.org/abs/2303.01469) ([paper](https://arxiv.org/pdf/2303.01469.pdf), [code](https://github.com/openai/consistency_models)) by Yang Song, Prafulla Dhariwal, Mark Chen, and Ilya Sutskever.
|
9 |
From the paper abstract:
|
10 |
|
@@ -42,7 +45,7 @@ The `diffusers` pipeline for the `cd_bedroom256_l2` model can be downloaded as f
|
|
42 |
```python
|
43 |
from diffusers import ConsistencyModelPipeline
|
44 |
|
45 |
-
pipe = ConsistencyModelPipeline.from_pretrained("
|
46 |
```
|
47 |
|
48 |
## Usage
|
@@ -58,7 +61,7 @@ from diffusers import ConsistencyModelPipeline
|
|
58 |
|
59 |
device = "cuda"
|
60 |
# Load the cd_bedroom256_l2 checkpoint.
|
61 |
-
model_id_or_path = "
|
62 |
pipe = ConsistencyModelPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
|
63 |
pipe.to(device)
|
64 |
|
|
|
3 |
tags:
|
4 |
- generative model
|
5 |
- unconditional image generation
|
6 |
+
- consistency-model
|
7 |
---
|
8 |
+
|
9 |
+
**Disclaimer**: This model was added by the amazing community contributor [dg845](https://huggingface.co/dg845) ❤️
|
10 |
+
|
11 |
Consistency models are a new class of generative models introduced in ["Consistency Models"](https://arxiv.org/abs/2303.01469) ([paper](https://arxiv.org/pdf/2303.01469.pdf), [code](https://github.com/openai/consistency_models)) by Yang Song, Prafulla Dhariwal, Mark Chen, and Ilya Sutskever.
|
12 |
From the paper abstract:
|
13 |
|
|
|
45 |
```python
|
46 |
from diffusers import ConsistencyModelPipeline
|
47 |
|
48 |
+
pipe = ConsistencyModelPipeline.from_pretrained("openai/diffusers-cd_bedroom256_l2")
|
49 |
```
|
50 |
|
51 |
## Usage
|
|
|
61 |
|
62 |
device = "cuda"
|
63 |
# Load the cd_bedroom256_l2 checkpoint.
|
64 |
+
model_id_or_path = "openai/diffusers-cd_bedroom256_l2"
|
65 |
pipe = ConsistencyModelPipeline.from_pretrained(model_id_or_path, torch_dtype=torch.float16)
|
66 |
pipe.to(device)
|
67 |
|