multimodalart HF Staff commited on
Commit
deb4167
·
verified ·
1 Parent(s): 6fe31a4

The keyframe half moved to multimodalart/minimax-h3

Browse files
Files changed (1) hide show
  1. README.md +2 -2
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 reference image, audio and video
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/diffusers-internal-dev/minimax-h3)
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