jzhang533/PaddleOCR-VL-For-Manga
vertexAI/publishers/hf-jzhang533/models/paddleocr-vl-for-manga@001
- Input modalities
- image, text
- Output modalities
- text
- Capabilities
- multimodal, visionInput
1 indexed models
1 matching models
vertexAI/publishers/hf-jzhang533/models/paddleocr-vl-for-manga@001
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.