Instructions to use zai-org/CogVideoX-5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use zai-org/CogVideoX-5b 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-5b", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
Upload VAE in fp32
#23
by a-r-r-o-w - opened
vae/config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKLCogVideoX",
|
| 3 |
-
"_diffusers_version": "0.
|
| 4 |
"act_fn": "silu",
|
| 5 |
"block_out_channels": [
|
| 6 |
128,
|
|
@@ -35,5 +35,6 @@
|
|
| 35 |
"CogVideoXUpBlock3D"
|
| 36 |
],
|
| 37 |
"use_post_quant_conv": false,
|
| 38 |
-
"use_quant_conv": false
|
|
|
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKLCogVideoX",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
"act_fn": "silu",
|
| 5 |
"block_out_channels": [
|
| 6 |
128,
|
|
|
|
| 35 |
"CogVideoXUpBlock3D"
|
| 36 |
],
|
| 37 |
"use_post_quant_conv": false,
|
| 38 |
+
"use_quant_conv": false,
|
| 39 |
+
"invert_scale_latents": false
|
| 40 |
}
|
vae/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e
|
| 3 |
+
size 862388596
|