FaceSwap_MiniMaxH3_REF2VA is an open-weight model from Whamu, released under Apache License 2.0. Its published files total 241.8 MB.
Changes the Reference video identity face with the Reference(s) one(s) - The LoRA is pruned from blocks under the set fro treshold (less heavy, less lora artifacts, identical strength to trained base) - Workflow is shared (CRT-Nodes), you can use your own…
Model Card
By Whamu, published under apache-2.0, revision d2d9d9717292.
Changes the Reference video identity face with the Reference(s) one(s) - The LoRA is pruned from blocks under the set fro treshold (less heavy, less lora artifacts, identical strength to trained base) - Workflow is shared (CRT-Nodes), you can use your own (make sure your input video respect the MH3 format) You can help me training cool models with runpod referal https://runpod.io?ref=u7b2habt so we both benefits, or with https://buymeacoffee.com/designedbycrt if you want to support these models. Thanks
Read Whamu's full model card
--- license: apache-2.0
- This LoRA applies on MiniMaxh3 ref2va model
- Changes the Reference video identity face with the Reference(s) one(s)
- Uses a single Trigger word (Faceswap)
- Uses at strenght 1
- The LoRA is pruned from blocks under the set fro treshold (less heavy, less lora artifacts, identical strength to trained base)
- Workflow is shared (CRT-Nodes), you can use your own (make sure your input video respect the MH3 format)
You can help me training cool models with runpod referal https://runpod.io?ref=u7b2habt so we both benefits, or with https://buymeacoffee.com/designedbycrt if you want to support these models. Thanks
Examples
More examples
Identity and Version
- Repository
- Wham13/FaceSwap_MiniMaxH3_REF2VA
- Publisher
- Whamu
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- d2d9d971729293b9767839a44825b20ac5e7af65
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
14 files, 241.8 MB in total. The weights are 1 file totalling 65.6 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| SS_FaceSwap_MiniMax_H3_REF2VA.safetensors | Weights | 65.6 MB | 1e032cf519cc |
| SS_FaceSwap_MiniMax REF2V.json | Configuration | 27.9 KB | — |
| README.md | Documentation | 2.4 KB | — |
| CRT-Nodes.png | Other | 795.3 KB | 7ffb68015775 |
| Workflow_Native_FaceSwap.zip | Other | 10.9 MB | 272634a51417 |
| videos/Faceswap_00013.mp4 | Other | 6.8 MB | 1e829f15f1e4 |
| videos/Faceswap_00039.mp4 | Other | 17.9 MB | 9952987bb60f |
| videos/Faceswap_00040.mp4 | Other | 18.3 MB | c9cb85632b39 |
| videos/Faceswap_00058.mp4 | Other | 17.2 MB | b4f89dc0d8e8 |
| videos/Faceswap_00107.mp4 | Other | 33.5 MB | dd7a629bafbb |
| videos/Faceswap_00109.mp4 | Other | 19.5 MB | 2292f391582e |
| videos/Faceswap_00114.mp4 | Other | 25.6 MB | 967449780d45 |
| videos/Faceswap_00120.mp4 | Other | 25.8 MB | e39e389d6ee7 |
| .gitattributes | Repository | 2.1 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 65.6 MB
Released by Whamu through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 65.6 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About FaceSwap_MiniMaxH3_REF2VA
Can I use FaceSwap_MiniMaxH3_REF2VA commercially?
Yes. FaceSwap_MiniMaxH3_REF2VA is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.