Instructions to use zai-org/CogView3-Plus-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/CogView3-Plus-3B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("zai-org/CogView3-Plus-3B", 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
Use `bfloat16` in the example
Browse files
README.md
CHANGED
|
@@ -62,7 +62,7 @@ Then, run the following code:
|
|
| 62 |
from diffusers import CogView3PlusPipeline
|
| 63 |
import torch
|
| 64 |
|
| 65 |
-
pipe = CogView3PlusPipeline.from_pretrained("THUDM/CogView3-Plus-3B", torch_dtype=torch.
|
| 66 |
|
| 67 |
# Enable it to reduce GPU memory usage
|
| 68 |
pipe.enable_model_cpu_offload()
|
|
|
|
| 62 |
from diffusers import CogView3PlusPipeline
|
| 63 |
import torch
|
| 64 |
|
| 65 |
+
pipe = CogView3PlusPipeline.from_pretrained("THUDM/CogView3-Plus-3B", torch_dtype=torch.bfloat16).to("cuda")
|
| 66 |
|
| 67 |
# Enable it to reduce GPU memory usage
|
| 68 |
pipe.enable_model_cpu_offload()
|