📊 Showing 4 results | 📏 Metric: TextVsionBlend OCR (F1 Score)
| Rank | Model | Paper | TextVsionBlend OCR (F1 Score) | Date | Code |
|---|---|---|---|---|---|
| 1 | Anytext | AnyText: Multilingual Visual Text Generation And Editing | 101.32 | 2023-11-06 | 📦 tyxsspa/anytext |
| 2 | TextDiffuser2 | TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering | 84.10 | 2023-11-28 | - |
| 3 | PixArt-Sigma | PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation | 72.62 | 2024-03-07 | 📦 PixArt-alpha/PixArt-sigma 📦 mindspore-lab/mindone |
| 4 | Infinity-2B | Infinity-MM: Scaling Multimodal Performance with Large-Scale and High-Quality Instruction Data | 71.59 | 2024-10-24 | 📦 LLaVA-VL/LLaVA-NeXT 📦 flagopen/flagscale 📦 BAAI/Aquila-VL-2B-llava-qwen 📦 BAAI/Infinity-MM |