akatz-ai/MiniMax-H3-Person-Remover-LoRA
video-to-video model by akatz-ai
Older snapshot: check the original source for current information.
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
[](https://x.com/akatzai) Original → Green mask → Person removed. Eight selected examples, shown with their full frames and original timing. Watch or download the 1080p comparison with original audio. Remove a selected person from a video and reconstruct the background with MiniMax H3 Ref2VA. The accompanying ComfyUI workflow tracks the person with SAM 3.1, fills the mask green, and generates the replacement background in overlapping windows. Supply the original video and a clean version of its first frame. Download the LoRA · Download the ComfyUI workflow · Training dataset This is an experimental adapter trained by Akatz Labs. The showcase contains selected successful results, not a benchmark of all inputs. Background details, camera movement, shadows, and hard cuts can still change. The Relay 2.0 workflow starts with no saved window locks or cache references. It uses native ComfyUI sampling, reference conditioning, SAM masks, loops and video saving, plus reusable Relay timeline…
Read the full model card ↗ · Preview checked 2026-11-01T03:56:33.984Z
Inside the original model card — Document outline
- MiniMax H3 Person Remover LoRA V1
- Quick start
- Required models
- Starting settings
- Training record
- Limitations
- License and attribution
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
akatz-ai/MiniMax-H3-Person-Remover-LoRA is a video-to-video model repository published by akatz-ai on Hugging Face. The source reports the diffusion-single-file library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- video-to-video
- Library
- diffusion-single-file
- Recent downloads (30 days)
- 1,270
- Cumulative likes
- 68
- Hugging Face trending score
- 65
- Reported safetensors parameters
- Not reported
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-10-08T04:00:03.000Z
- Last modified
- 2026-10-10T07:43:33.000Z
Compatibility and lineage
Reported languages: en
Reported base models: Comfy-Org/MiniMax-H3
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-10-15T06:41:17.732Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.
Related models
akatz-ai/MiniMax-H3-Character-Swap-LoRA
Lightricks/LTX-2.5-22b-IC-LoRA-Alpha-Gen
Lightricks/LTX-2.5-22b-IC-LoRA-Layout-To-Render
Lightricks/LTX-2.5-22b-IC-LoRA-Restore