v33ts commited on
Commit
6cddb49
·
verified ·
1 Parent(s): 97bd040

Upload models/vae/cog/cogvideox_vae_fp32.md with huggingface_hub

Browse files
models/vae/cog/cogvideox_vae_fp32.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ author: cogvideox996
3
+ baseModel: CogVideoX
4
+ hashes:
5
+ AutoV1: 8A96607E
6
+ AutoV2: A410E48D98
7
+ AutoV3: 37ABB2444528
8
+ BLAKE3: F475F5AD96B6BB2A791A0DDD2C055810E4C12A4343CDD926BC2ED3B9ACE25FCD
9
+ CRC32: 1AB3FB12
10
+ SHA256: A410E48D988C8224CEF392B68DB0654485CFD41F345F4A3A81D3E6B765BB995E
11
+ metadata:
12
+ format: SafeTensor
13
+ modelPage: https://civitai.com/models/1009676?modelVersionId=1131953
14
+ preview:
15
+ - https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/39402559-7cc5-4e33-b8ff-895ad0769b60/width=450/43812071.jpeg
16
+ website: Civitai
17
+ ---
18
+
19
+ # Trigger Words
20
+
21
+ No trigger words
22
+
23
+ # About this version
24
+
25
+ * **SHA256:** a410e48d988c8224cef392b68db0654485cfd41f345f4a3a81d3e6b765bb995e
26
+ * **Pointer size:** 134 Bytes
27
+ * **Size of remote file:** 862 MB
28
+
29
+ # CogVideoX-VAE
30
+
31
+ The model is released under a permissive CogVideoX license.
32
+
33
+ To get started with ComfyUI;
34
+
35
+ 1. Update to the latest version of ComfyUI
36
+ 2. Download CogVideoX model weights into `models/diffusion_models` folder, use "CogVideoXModelLoader" load
37
+ 3. Make sure a text encoder [[1](https://civitai.com/models/497255?modelVersionId=568405)] is in your `models/clip` folder
38
+ 4. Download the VAE to: `ComfyUI/models/vae, use "`CogVideoXVAELoader`" load`
39
+
40
+
41
+ CogVideoX has [kijai ComfyUI support](https://github.com/kijai/ComfyUI-CogVideoXWrapper), and will run on 20GB+ or 9GB VRAM.
42
+
43
+ Github: <https://github.com/THUDM/CogVideo>
44
+
45
+ HuggingFace: <https://huggingface.co/collections/THUDM/cogvideo-66c08e62f1685a3ade464cce>