You can deploy this model and start earning money today!

AEmotionStudio/
minimax-remover

zibojia/minimax-remover

finetune

cc-by-nc-4.0

Views

No views yet

MiniMax-Remover — Video Object Removal

Mirror of zibojia/minimax-remover for use with ComfyUI-FFMPEGA.

What is MiniMax-Remover?

MiniMax-Remover is a purpose-built DiT (Diffusion Transformer) model for video object removal. Given a video and a binary mask indicating unwanted regions, the model inpaints the masked areas with temporally consistent content.

Key features:

81-frame native batch size — processes up to 81 frames at once for temporal consistency
6–12 inference steps — fast inference with iterative mask dilation
Simplified DiT architecture — lightweight compared to general-purpose video editors (~2.5 GB)

Files

transformer/diffusion_pytorch_model.safetensors   (~2.25 GB)
vae/diffusion_pytorch_model.safetensors            (~508 MB)
scheduler/scheduler_config.json

Usage

With ComfyUI-FFMPEGA (recommended)

Enable the use_minimax_remover toggle on the FFMPEG Agent node
Use auto_mask:effect=remove or select minimax_remover no-LLM mode
The model auto-downloads on first use

Manual download

huggingface-cli download AEmotionStudio/minimax-remover --local-dir ./minimax_remover

Programmatic

python

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="AEmotionStudio/minimax-remover",
    allow_patterns=["vae/*", "transformer/*", "scheduler/*"],
    local_dir="./minimax_remover"
)

Removal Priority in FFMPEGA

When used with ComfyUI-FFMPEGA, MiniMax-Remover has the highest priority for object removal:

MiniMax-Remover (~2.5 GB VRAM) — when use_minimax_remover=On
FLUX Klein 4B (~15 GB VRAM) — when use_flux_klein=On
LaMa (~200 MB VRAM) — always available fallback
Black fill (0 VRAM) — FFmpeg fallback

⚠️ License

Non-Commercial Use Only: Model weights are licensed under CC-BY-NC-4.0. The source code is Apache 2.0.

Users must accept the non-commercial license terms when downloading. Commercial use of the model weights requires separate licensing from the original authors.

Credits

Original model by: Jiaqi Zhu et al.
Paper: "MiniMax-Remover: Taming Bad Noise Helps Video Object Removal"
Upstream HuggingFace: zibojia/minimax-remover
Redistributed by: Æmotion Studio for use with ComfyUI-FFMPEGA