Total runs:
85.3K
Run Growth:
10.3K
Growth Rate:
11.29%
Sponsored by
APIMart
alibaba-pai / MiniMax-H3-Fun-Controlnet-Union
Model's Last Updated: September 22 2026
text-to-video
Introduction of MiniMax-H3-Fun-Controlnet-Union
Model Details of MiniMax-H3-Fun-Controlnet-Union
MiniMax-H3-Fun-Controlnet-Union
MiniMax-H3-Fun-Controlnet-Union is a ControlNet-Union for MiniMax-H3 , trained with the VideoX-Fun pipeline. A single checkpoint conditions the MiniMax-H3 video generator on Canny, Depth, HED, MLSD or Pose control videos, and also runs video inpainting.
Model Card
| Name | Description |
|---|---|
| MiniMax-H3-Fun-Controlnet-Union.safetensors |
ControlNet-Union branch weights for MiniMax-H3. The file holds only the control branch (
control_proj_in
plus 5
control_blocks
, about 6.8 GB) and is loaded on top of the base MiniMax-H3 transformer. One checkpoint supports Canny, Depth, HED, MLSD and Pose control conditions, and video inpainting.
|
Model Features
- Union control: one checkpoint handles Canny, Depth, HED, MLSD and Pose control videos for video-to-video generation, no per-condition checkpoint switching.
- The control branch attaches to 5 of the 50 transformer blocks (layers 0, 10, 20, 30, 40); every control skip is added to the main branch through a zero-gated projection.
-
Guidance-distilled: run with
guidance_scale = 1.0, one forward pass per step, no classifier-free guidance needed. -
Inpainting is supported: the control input is widened to
control_in_dim = 49(latent + masked latent + mask channels); useexamples/minimax_h3_fun/predict_v2v_control_inpaint.py. -
control_context_scalescales every control skip before it is added to the main branch:1.0gives the strongest control (used for all results below), values below1.0weaken the guidance of the control video,0.0switches the control branch off. -
The generation follows the control video: the frame count snaps down to the largest
17 * n + 5the video VAE can decode (duration capped at 15 seconds), the canvas keeps the control video's own aspect ratio at theheight * widthpixel budget (both multiples of 32), at a fixed 24 fps. - Detailed prompts give better stability; we recommend describing the scene, the subject and the camera in the prompt.
Results
All samples below are generated with
num_inference_steps = 40
,
guidance_scale = 1.0
,
control_context_scale = 1.00
, seed 43.
Canny
| Control | Output |
Depth
| Control | Output |
HED
| Control | Output |
MLSD
| Control | Output |
Pose
| Control | Output |
Inference
Go to the VideoX-Fun repository for more details.
Please clone the VideoX-Fun repository and create the required directories:
# Clone the code
git clone https://github.com/aigc-apps/VideoX-Fun.git
# Enter VideoX-Fun's directory
cd VideoX-Fun
# Create model directories
mkdir -p models/Diffusion_Transformer
Then download the base MiniMax-H3 model and this checkpoint into
models/Diffusion_Transformer
.
📦 models/
├── 📂 Diffusion_Transformer/
│ ├── 📂 MiniMax-H3/
│ └── 📂 MiniMax-H3-Fun-Controlnet-Union/
│ └── 📦 MiniMax-H3-Fun-Controlnet-Union.safetensors
Then edit the settings at the top of
examples/minimax_h3_fun/predict_v2v_control.py
and run it.
model_name = "models/Diffusion_Transformer/MiniMax-H3"
config_path = "config/minimax_h3/minimax_h3_control.yaml"
transformer_path = "models/Diffusion_Transformer/MiniMax-H3-Fun-Controlnet-Union/MiniMax-H3-Fun-Controlnet-Union.safetensors"
control_video = "your_control_video.mp4"
prompt = "your prompt"
python examples/minimax_h3_fun/predict_v2v_control.py
Notes:
-
config_pathmust build the control branch exactly as trained (control_blocks_places: [0, 10, 20, 30, 40],control_in_dim: 49,control_apply_audio: false); a mismatched layout makes the checkpoint fail to load. -
The checkpoint is guidance-distilled: keep
guidance_scale = 1.0; a value above 1 applies guidance twice and degrades the output. -
The control checkpoint carries only the control branch; the base MiniMax-H3 weights must be present in
model_name. -
Memory: the transformer (about 62 GB) plus the Qwen3-VL text encoder (about 62 GB) do not fit one 80 GB GPU fully loaded; use
model_group_offload(fastest) ormodel_cpu_offload_and_qfloat8on a single 80 GB GPU.
License
This model is a derivative of MiniMax-H3 and is released under the MiniMax H3 Community License Agreement . Please read the license carefully, especially the territorial restrictions and the Acceptable Use Policy, before use.
Runs of alibaba-pai MiniMax-H3-Fun-Controlnet-Union on huggingface.co
11.7K
Total runs
0
24-hour runs
-361
3-day runs
-1.9K
7-day runs
4.0K
30-day runs
More Information About MiniMax-H3-Fun-Controlnet-Union huggingface.co Model
Url of MiniMax-H3-Fun-Controlnet-Union
MiniMax-H3-Fun-Controlnet-Union huggingface.co Url
Provider of MiniMax-H3-Fun-Controlnet-Union huggingface.co
Other API from alibaba-pai
Updated:February 26 2026
Total runs:
61.9K
Run Growth:
12.7K
Growth Rate:
20.54%
Total runs:
59.9K
Run Growth:
5.4K
Growth Rate:
9.13%
Total runs:
37.0K
Run Growth:
37.0K
Growth Rate:
100.00%
Total runs:
35.1K
Run Growth:
32.1K
Growth Rate:
95.02%
Total runs:
22.7K
Run Growth:
-11.6K
Growth Rate:
-50.91%
Total runs:
21.5K
Run Growth:
20.6K
Growth Rate:
96.08%
Total runs:
16.9K
Run Growth:
16.1K
Growth Rate:
95.24%
Total runs:
15.1K
Run Growth:
5.2K
Growth Rate:
34.45%
Total runs:
13.6K
Run Growth:
13.6K
Growth Rate:
100.00%
Total runs:
11.7K
Run Growth:
32
Growth Rate:
0.27%
Total runs:
9.8K
Run Growth:
5.3K
Growth Rate:
54.29%
Total runs:
9.4K
Run Growth:
6.1K
Growth Rate:
64.44%
Total runs:
7.6K
Run Growth:
6.8K
Growth Rate:
89.29%
Total runs:
7.5K
Run Growth:
4.3K
Growth Rate:
44.68%
Total runs:
6.7K
Run Growth:
460
Growth Rate:
6.86%
Total runs:
5.2K
Run Growth:
315
Growth Rate:
6.06%
Total runs:
4.9K
Run Growth:
2.2K
Growth Rate:
48.88%
Total runs:
4.6K
Run Growth:
4.2K
Growth Rate:
90.93%
Total runs:
4.1K
Run Growth:
-677
Growth Rate:
-16.14%
Total runs:
4.0K
Run Growth:
3.8K
Growth Rate:
96.24%
Total runs:
1.8K
Run Growth:
900
Growth Rate:
50.42%
Total runs:
1.7K
Run Growth:
1.2K
Growth Rate:
71.55%
Total runs:
1.6K
Run Growth:
883
Growth Rate:
54.31%
Total runs:
1.3K
Run Growth:
-971
Growth Rate:
-72.19%
Total runs:
1.2K
Run Growth:
1.1K
Growth Rate:
91.10%
Total runs:
1.0K
Run Growth:
96
Growth Rate:
9.22%
Total runs:
612
Run Growth:
345
Growth Rate:
55.74%
Total runs:
501
Run Growth:
65
Growth Rate:
12.97%
Total runs:
388
Run Growth:
4
Growth Rate:
1.03%
Total runs:
379
Run Growth:
164
Growth Rate:
43.27%
Total runs:
340
Run Growth:
10
Growth Rate:
2.94%
Total runs:
338
Run Growth:
265
Growth Rate:
78.87%
Total runs:
283
Run Growth:
105
Growth Rate:
35.71%
Total runs:
265
Run Growth:
15
Growth Rate:
5.66%
Total runs:
262
Run Growth:
208
Growth Rate:
79.39%
Total runs:
252
Run Growth:
-391
Growth Rate:
-155.16%
Total runs:
234
Run Growth:
-36
Growth Rate:
-15.38%
Total runs:
216
Run Growth:
-1.9K
Growth Rate:
-903.40%
Total runs:
198
Run Growth:
139
Growth Rate:
70.20%
Total runs:
193
Run Growth:
127
Growth Rate:
65.80%
Total runs:
191
Run Growth:
10
Growth Rate:
5.43%
Total runs:
186
Run Growth:
115
Growth Rate:
68.05%
Total runs:
185
Run Growth:
-51
Growth Rate:
-27.57%
Total runs:
137
Run Growth:
7
Growth Rate:
5.11%
Total runs:
125
Run Growth:
-123
Growth Rate:
-98.40%
Total runs:
121
Run Growth:
-57
Growth Rate:
-47.50%
Total runs:
120
Run Growth:
61
Growth Rate:
50.83%
Total runs:
119
Run Growth:
-9
Growth Rate:
-7.56%
Total runs:
108
Run Growth:
29
Growth Rate:
26.85%
Total runs:
106
Run Growth:
84
Growth Rate:
79.25%
Total runs:
83
Run Growth:
3
Growth Rate:
3.61%
Total runs:
82
Run Growth:
-16
Growth Rate:
-19.51%
Total runs:
66
Run Growth:
-15
Growth Rate:
-22.73%
Total runs:
62
Run Growth:
37
Growth Rate:
59.68%
Total runs:
59
Run Growth:
29
Growth Rate:
49.15%
Total runs:
57
Run Growth:
9
Growth Rate:
15.79%
Total runs:
55
Run Growth:
28
Growth Rate:
50.91%
Total runs:
50
Run Growth:
28
Growth Rate:
56.00%
Total runs:
44
Run Growth:
26
Growth Rate:
59.09%
Total runs:
36
Run Growth:
32
Growth Rate:
88.89%
Total runs:
31
Run Growth:
14
Growth Rate:
45.16%
Total runs:
29
Run Growth:
-71
Growth Rate:
-244.83%
Total runs:
27
Run Growth:
19
Growth Rate:
70.37%
Total runs:
26
Run Growth:
2
Growth Rate:
7.69%
Total runs:
26
Run Growth:
16
Growth Rate:
61.54%
Total runs:
25
Run Growth:
-14
Growth Rate:
-56.00%
Total runs:
25
Run Growth:
1
Growth Rate:
4.00%
Total runs:
24
Run Growth:
20
Growth Rate:
83.33%
Total runs:
20
Run Growth:
-2
Growth Rate:
-10.00%
Total runs:
19
Run Growth:
3
Growth Rate:
15.79%
Total runs:
19
Run Growth:
-4
Growth Rate:
-21.05%
Total runs:
18
Run Growth:
5
Growth Rate:
27.78%
Total runs:
18
Run Growth:
5
Growth Rate:
27.78%
Total runs:
17
Run Growth:
6
Growth Rate:
35.29%
Total runs:
17
Run Growth:
-3
Growth Rate:
-17.65%
Total runs:
15
Run Growth:
1
Growth Rate:
6.67%
Total runs:
15
Run Growth:
13
Growth Rate:
86.67%
Total runs:
15
Run Growth:
-5
Growth Rate:
-35.71%
Total runs:
15
Run Growth:
3
Growth Rate:
20.00%
Total runs:
15
Run Growth:
1
Growth Rate:
6.67%
Total runs:
14
Run Growth:
-10
Growth Rate:
-71.43%
Total runs:
13
Run Growth:
9
Growth Rate:
69.23%
Total runs:
12
Run Growth:
6
Growth Rate:
50.00%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
12
Run Growth:
8
Growth Rate:
66.67%
Total runs:
12
Run Growth:
1
Growth Rate:
8.33%
Total runs:
11
Run Growth:
4
Growth Rate:
36.36%
Total runs:
11
Run Growth:
7
Growth Rate:
63.64%
Total runs:
11
Run Growth:
4
Growth Rate:
36.36%
Total runs:
10
Run Growth:
1
Growth Rate:
10.00%
Total runs:
10
Run Growth:
4
Growth Rate:
40.00%
Total runs:
10
Run Growth:
-1
Growth Rate:
-10.00%
Total runs:
10
Run Growth:
6
Growth Rate:
60.00%
Total runs:
10
Run Growth:
-3
Growth Rate:
-30.00%
Total runs:
9
Run Growth:
1
Growth Rate:
11.11%
Total runs:
9
Run Growth:
-4
Growth Rate:
-44.44%
Total runs:
9
Run Growth:
1
Growth Rate:
11.11%
Total runs:
9
Run Growth:
5
Growth Rate:
55.56%