Instructions to use zai-org/CogVideoX-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/CogVideoX-2b 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/CogVideoX-2b", 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
Update vae config to remove unused parameters
#9
by a-r-r-o-w - opened
- vae/config.json +0 -2
vae/config.json
CHANGED
|
@@ -20,11 +20,9 @@
|
|
| 20 |
"latents_mean": null,
|
| 21 |
"latents_std": null,
|
| 22 |
"layers_per_block": 3,
|
| 23 |
-
"mid_block_add_attention": true,
|
| 24 |
"norm_eps": 1e-06,
|
| 25 |
"norm_num_groups": 32,
|
| 26 |
"out_channels": 3,
|
| 27 |
-
"sample_size": 256,
|
| 28 |
"scaling_factor": 1.15258426,
|
| 29 |
"shift_factor": null,
|
| 30 |
"temporal_compression_ratio": 4,
|
|
|
|
| 20 |
"latents_mean": null,
|
| 21 |
"latents_std": null,
|
| 22 |
"layers_per_block": 3,
|
|
|
|
| 23 |
"norm_eps": 1e-06,
|
| 24 |
"norm_num_groups": 32,
|
| 25 |
"out_channels": 3,
|
|
|
|
| 26 |
"scaling_factor": 1.15258426,
|
| 27 |
"shift_factor": null,
|
| 28 |
"temporal_compression_ratio": 4,
|