Florence2
Implementing the Florence-2-base model for image understanding. Supports captioning, OCR, and object detection with optional phrase grounding. Uses ONNX models from huggingface.co/onnx-community/Florence-2-base. Enables various output tasks including detailed captioning, region-based OCR, and flexible object detection.
Activity
- Latest release
- 9mo ago
- Total releases
- 14
- Cadence
- ~daily
- Last 12 months
- 3
Details
- License
- MIT
- First release
- Jul 23, 2024
| Version | Released | |
|---|---|---|
25.12.63049
patch
|
25.12.63049
patch
Dependencies (5)
|
|
25.12.63048
patch
|
25.12.63048
patch
Dependencies (5)
|
|
25.12.63047
minor
|
25.12.63047
minor
Dependencies (5)
|
|
25.7.59767
major
|
25.7.59767
major
Dependencies (5)
|
|
24.11.53800
patch
|
24.11.53800
patch
Dependencies (5)
|
|
24.11.53799
minor
|
24.11.53799
minor
Dependencies (5)
|
|
24.10.53218
minor
|
24.10.53218
minor
Dependencies (5)
|
|
24.9.51644
minor
|
24.9.51644
minor
Dependencies (5)
|
|
24.7.50588
patch
|
24.7.50588
patch
Dependencies (5)
|
|
24.7.50576
patch
|
24.7.50576
patch
Dependencies (5)
|
|
24.7.50575
patch
|
24.7.50575
patch
Dependencies (5)
|
|
24.7.50572
patch
|
24.7.50572
patch
Dependencies (5)
|
|
24.7.50455
patch
|
24.7.50455
patch
Dependencies (6)
|
|
24.7.50454
initial
|
24.7.50454
initial
Dependencies (6)
|