All tasks / Tools
Amuse
Desktop app for running image, video and audio models locally, with ONNX, GGUF and safetensors support and an editor.
- TensorStack
- Local only
- Free, open source
Where it ranks
- BImage generationApps · Local · via Qwen-Image-2.1
- BImage editingApps · Local · via Qwen-Image-2.1
- –Upscaling & restorationApps · Local · no rated model available here yet
- CVideo generationApps · Local · via Wan 2.2
Tools without a benchmark of their own inherit the tier of the best model they offer.
Facts
- Vendor
- TensorStack
- Approach
- Apps
- Where it runs
- Runs only on your own hardware
- Interface
- Desktop app
- Skill level
- Beginner: works out of the box
- Price
- Free, open source
- Pricing notes
- Free and open source; latest release v3.8.4 (2026-10-16).
- Source code
- Open source (Apache-2.0)
- GitHub stars
- 635 (19 Oct 2026)
- Last verified
- 19 Oct 2026
Price from github.com, 19 Oct 2026.
Models it gives you
- BQwen-Image-2.1Alibaba (Qwen) · open weights
- CFLUX.2 [dev]Black Forest Labs · open weights
- CHiDream-O1-ImageHiDream.ai · open weights
- CZ-Image TurboAlibaba (Tongyi-MAI) · open weights
- CERNIE-Image-TurboBaidu · open weights
- CKrea 2 TurboKrea · open weights
- CGLM-ImageZ.ai · open weights
- CLongCat-ImageMeituan (LongCat) · open weights
- CWan 2.2Alibaba (Wan-AI) · open weights
- –FLUX 3 Image KleinBlack Forest Labs · open weights
- –JoyAI-Image Edit PlusJD (JD Open Source) · open weights