The keyframe half moved to multimodalart/minimax-h3
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ sdk: gradio
|
|
| 7 |
sdk_version: 6.20.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
-
short_description: MiniMax-H3
|
| 11 |
suggested_hardware: zero-a10g
|
| 12 |
---
|
| 13 |
|
|
@@ -20,7 +20,7 @@ This Space is the denoising half of the `ref2va` task: the 61.73 GiB `transforme
|
|
| 20 |
autoencoders. The 62.14 GiB Qwen3-VL conditioner runs in
|
| 21 |
[`qwen3vl-conditioner`](https://huggingface.co/spaces/multimodalart/qwen3vl-conditioner), which this
|
| 22 |
Space calls over the gradio API for every request — the same conditioner Space, and the same resident weights, that
|
| 23 |
-
the keyframe half [`minimax-h3`](https://huggingface.co/spaces/
|
| 24 |
uses.
|
| 25 |
|
| 26 |
## Why split
|
|
|
|
| 7 |
sdk_version: 6.20.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
short_description: Unquantized MiniMax-H3 from image, audio, video refs
|
| 11 |
suggested_hardware: zero-a10g
|
| 12 |
---
|
| 13 |
|
|
|
|
| 20 |
autoencoders. The 62.14 GiB Qwen3-VL conditioner runs in
|
| 21 |
[`qwen3vl-conditioner`](https://huggingface.co/spaces/multimodalart/qwen3vl-conditioner), which this
|
| 22 |
Space calls over the gradio API for every request — the same conditioner Space, and the same resident weights, that
|
| 23 |
+
the keyframe half [`minimax-h3`](https://huggingface.co/spaces/multimodalart/minimax-h3)
|
| 24 |
uses.
|
| 25 |
|
| 26 |
## Why split
|