Model reference · open weights
videoprism-f16r288-pt is an open-weight embedding model from sposiboh. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | sposiboh |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 114M |
| Runs with | transformers |
| Released | 2026-05-09 |
| Popularity | 1k downloads / month |
| Licence | Open weights |
About
PyTorch port of google/videoprism-base-f16r288 (Google DeepMind's VideoPrism). The original release ships JAX/Flax weights only; this repo hosts a self-contained PyTorch implementation that produces numerically-equivalent outputs (cosine sim 1.000000 vs the JAX reference). Source: .
from transformers import AutoModel, AutoProcessor
model = AutoModel.from_pretrained("sposiboh/videoprism-base-f16r288-pt", trust_remote_code=True)
processor = AutoProcessor.from_pretrained("sposiboh/videoprism-base-f16r288-pt", trust_remote_code=True)
# Process a video file (or a list of frames / numpy / torch tensor):
inputs = processor(videos="path/to/video.mp4", return_tensors="pt")
outputs = model(**inputs)
embedding = outputs.last_hidden_state # shape: (B, T*N, model_dim) — token sequence
Frames are sampled uniformly to the model's native frame count and resized
bilinearly to image_size × image_size. Pixels are scaled to [0, 1].
If you use this model, please cite the original VideoPrism paper:
@inproceedings{zhao2024videoprism,
title = {VideoPrism: A Foundational Visual Encoder for Video Understanding},
author = {Zhao, Long and Gundavarapu, Nitesh B. and Yuan, Liangzhe and Zhou, Hao and Yan, Shen and Sun, Jennifer J. and Friedman, Luke and Qian, Rui and Weyand, Tobias and Zhao, Yue and Hornung, Rachel and Schroff, Florian and Yang, Ming-Hsuan and Ross, David A. and Wang, Huisheng and Adam, Hartwig and Sirotenko, Mikhail and Liu, Ting and Gong, Boqing},
booktitle = {ICML},
year = {2024},
}
Apache-2.0 (matches upstream license).
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys videoprism-f16r288-pt for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (videoprism-f16r288-pt below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"videoprism-f16r288-pt","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.