Model Tracker
ImageBind
ImageBind is an AI model made by Meta. Meta released it on 9 May 2023. It is generally available. Its weights are open.
- Released
- 9 May 2023 — ai.meta.com, read 16 October 2026
- Status
- Generally available — github.com, read 16 October 2026
- Takes
- Image, Video, Text, Audio — github.com, read 16 October 2026
- Returns
- Not confirmed: The model card says the model returns an embedding. An embedding is not one of the register's allowed output types (text, image, audio, video, code).
- Open weights
- Yes — github.com, read 16 October 2026
- Licence
- Not confirmed: two readings disagree: Attribution-NonCommercial-ShareAlike 4.0 International and CC BY-NC 4.0
- Context window
- Not confirmed: The official model card and repository do not print a context-window limit in tokens.
- Longest answer
- Not confirmed: The official model card and repository do not print a maximum output limit in tokens.
- Knowledge cutoff
- Not confirmed: The official pages reviewed do not state a knowledge-cutoff date.
- API price, input
- Not confirmed: The official pages reviewed provide downloadable weights and code, but no standard API input price per 1,000,000 tokens.
- API price, output
- Not confirmed: The official pages reviewed provide downloadable weights and code, but no standard API output price per 1,000,000 tokens.
- Where
- Downloadable weights — github.com, read 16 October 2026
- Parameters
- Not confirmed: The official model card, repository, and announcement do not state a parameter count.
- Model card
- https://github.com/facebookresearch/ImageBind/blob/main/model_card.md — github.com, read 16 October 2026
Questions
When was ImageBind released?
Meta released ImageBind on 9 May 2023.
Is ImageBind still available?
Yes: it is generally available, as Meta states it.
Are the weights of ImageBind open?
Yes: Meta publishes the weights of ImageBind for download.
More from Meta
- Audiobox
- AudioGen
- Chameleon
- CM3leon
- Code Llama
- DINOv2
- DINOv3
- Emu
- Emu Edit
- Emu Video
- EnCodec
- I-JEPA
- LLaMA
- Llama 2
- Llama 3
- Llama 3.1
- Llama 3.2
- Llama 3.3
- Llama 4 Maverick
- Llama 4 Scout
- M2M-100
- Make-A-Video
- Movie Gen
- Multi-Band Diffusion
Sources
- ImageBind: Holistic AI learning across six modalities (read 16 October 2026)
- ImageBind: One Embedding Space To Bind Them All (read 16 October 2026)
- Model Card for ImageBind (read 16 October 2026)
- ImageBind LICENSE (read 16 October 2026)