update model card
Browse files
README.md
CHANGED
@@ -65,10 +65,6 @@ aesthetic prompts. Specifically, Stable Cascade (30 inference steps) was compare
|
|
65 |
steps), SDXL (50 inference steps), SDXL Turbo (1 inference step) and Würstchen v2 (30 inference steps).
|
66 |
|
67 |
## Code Example
|
68 |
-
```shell
|
69 |
-
#install `diffusers` from this branch while the PR is WIP
|
70 |
-
pip install git+https://github.com/kashif/diffusers.git@wuerstchen-v3
|
71 |
-
```
|
72 |
|
73 |
```python
|
74 |
import torch
|
@@ -78,8 +74,8 @@ device = "cuda"
|
|
78 |
dtype = torch.bfloat16
|
79 |
num_images_per_prompt = 2
|
80 |
|
81 |
-
prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", torch_dtype=
|
82 |
-
decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", torch_dtype=
|
83 |
|
84 |
prompt = "Anthropomorphic cat dressed as a pilot"
|
85 |
negative_prompt = ""
|
@@ -135,4 +131,4 @@ The model is intended for research purposes only.
|
|
135 |
|
136 |
## How to Get Started with the Model
|
137 |
|
138 |
-
Check out https://github.com/Stability-AI/StableCascade
|
|
|
65 |
steps), SDXL (50 inference steps), SDXL Turbo (1 inference step) and Würstchen v2 (30 inference steps).
|
66 |
|
67 |
## Code Example
|
|
|
|
|
|
|
|
|
68 |
|
69 |
```python
|
70 |
import torch
|
|
|
74 |
dtype = torch.bfloat16
|
75 |
num_images_per_prompt = 2
|
76 |
|
77 |
+
prior = StableCascadePriorPipeline.from_pretrained("stabilityai/stable-cascade-prior", torch_dtype=torch.bfloat16).to(device)
|
78 |
+
decoder = StableCascadeDecoderPipeline.from_pretrained("stabilityai/stable-cascade", torch_dtype=torch.float16).to(device)
|
79 |
|
80 |
prompt = "Anthropomorphic cat dressed as a pilot"
|
81 |
negative_prompt = ""
|
|
|
131 |
|
132 |
## How to Get Started with the Model
|
133 |
|
134 |
+
Check out https://github.com/Stability-AI/StableCascade
|