Apple Ferret
1 like
An end-to-end MLLM that accept any-form referring and ground anything in response.
Features
- Image recognition
- AI-Powered
- AI Writing
Tags
- multi-model-ai-integration
- apple-ferret
- Artificial intelligence
- multimodal
Apple Ferret News & Activities
Highlights All activities
Recent News
No news, maybe you know any news worth sharing?
Share a News TipRecent activities
Miguel5252 added Apple Ferret as alternative to LumeDream
mockit added Apple Ferret as alternative to Mock It AI
rajivmeno22 added Apple Ferret as alternative to Lexica AI
artganic added Apple Ferret as alternative to Artganic.me
duanhjlt added Apple Ferret as alternative to StringArtGenerator
POX added Apple Ferret as alternative to Qwen Image
Mickeynerd637 added Apple Ferret as alternative to PlasmaArt AI
POX added Apple Ferret as alternative to BAGEL AI
phototovideo added Apple Ferret as alternative to 4o Image
mikehalloweenfine added Apple Ferret as alternative to AI Cartoon Generator
Apple Ferret information
Developed by
Apple Licensing
Open Source and Free Personal product.Written in
Alternatives
76 alternatives listedSupported Languages
- English
AlternativeTo Category
AI Tools & ServicesGitHub repository
- 8,670 Stars
- 518 Forks
- 7 Open Issues
- Updated
No comments or reviews, maybe you want to be first?
Post comment/reviewWhat is Apple Ferret?
An end-to-end MLLM that accept any-form referring and ground anything in response.
Key Contributions:
- Ferret Model - Hybrid Region Representation + Spatial-aware Visual Sampler enable fine-grained and open-vocabulary referring and grounding in MLLM.
- GRIT Dataset (~1.1M) - A Large-scale, Hierarchical, Robust ground-and-refer instruction tuning dataset.
- Ferret-Bench - A multimodal evaluation benchmark that jointly requires Referring/Grounding, Semantics, Knowledge, and Reasoning.
Usage and License Notices: The data, and code is intended and licensed for research use only. They are also restricted to uses that follow the license agreement of LLaMA, Vicuna and GPT-4. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.