Upload models/vae/mochi_vae.md with huggingface_hub
Browse files- models/vae/mochi_vae.md +54 -0
models/vae/mochi_vae.md
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
author: theally
|
| 3 |
+
baseModel: Mochi
|
| 4 |
+
hashes:
|
| 5 |
+
AutoV1: C5334E79
|
| 6 |
+
AutoV2: 1BE451CEC9
|
| 7 |
+
AutoV3: ECE5DC12F490
|
| 8 |
+
BLAKE3: 36164206DC087B77C3B01C82176EC560E0658DA0FE7F0D27826A74177471AB06
|
| 9 |
+
CRC32: D1349C99
|
| 10 |
+
SHA256: 1BE451CEC94B911980406169286BABC5269E7CF6A94BBBBDF45E8D3F2C961083
|
| 11 |
+
metadata:
|
| 12 |
+
format: SafeTensor
|
| 13 |
+
fp: fp8
|
| 14 |
+
size: pruned
|
| 15 |
+
modelPage: https://civitai.com/models/922390?modelVersionId=1035187
|
| 16 |
+
preview:
|
| 17 |
+
- https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/2d275e3b-6b77-489d-8ea8-6376cb462ead/width=450/38738187.jpeg
|
| 18 |
+
- https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/10f28599-4463-46d1-b164-83b658ff50fc/width=450/38738195.jpeg
|
| 19 |
+
website: Civitai
|
| 20 |
+
---
|
| 21 |
+
|
| 22 |
+
# Trigger Words
|
| 23 |
+
|
| 24 |
+
No trigger words
|
| 25 |
+
|
| 26 |
+
# About this version
|
| 27 |
+
|
| 28 |
+
No description about this version
|
| 29 |
+
|
| 30 |
+
# Mochi 1 Preview - Video Model
|
| 31 |
+
|
| 32 |
+
Read our [Quickstart Guide to Mochi](https://education.civitai.com/civitais-quickstart-guide-to-mochi-1-text2video/) on the Civitai Education Hub!
|
| 33 |
+
|
| 34 |
+
If you don't want to run it locally, **you can try it out now on the Civitai Generator**! Read the [Guide to Video Generation in the Civitai Generator](https://education.civitai.com/civitais-guide-to-video-in-the-civitai-generator/)!
|
| 35 |
+
|
| 36 |
+
**Mochi 1 preview,** by creators <https://www.genmo.ai>**,** is an open state-of-the-art video generation model with high-fidelity motion and strong prompt adherence in preliminary evaluation.
|
| 37 |
+
|
| 38 |
+
This model dramatically closes the gap between closed and open video generation systems.
|
| 39 |
+
|
| 40 |
+
The model is released under a permissive Apache 2.0 license.
|
| 41 |
+
|
| 42 |
+
To get started with ComfyUI;
|
| 43 |
+
|
| 44 |
+
1. Update to the latest version of ComfyUI
|
| 45 |
+
2. Download Mochi model weights into `models/diffusion_models` folder
|
| 46 |
+
3. Make sure a text encoder [[1](https://civitai.com/models/497255?modelVersionId=568405)][[2](https://civitai.com/models/497255?modelVersionId=568485)] is in your `models/clip` folder
|
| 47 |
+
4. Download the VAE to: `ComfyUI/models/vae`
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
Mochi has [native ComfyUI support](https://blog.comfy.org/mochi-1/), and will run on 12GB+ VRAM.
|
| 51 |
+
|
| 52 |
+
Github: <https://github.com/genmoai/models>
|
| 53 |
+
|
| 54 |
+
HuggingFace: <https://huggingface.co/genmo/mochi-1-preview>
|