# Visual Text Generation

Direct GGUF conversion version of Wan2.1-T2V-1.3B, suitable for text-to-video generation tasks on consumer-grade GPUs

Gemma 3 is Google's lightweight open model series based on Gemini technology, supporting multimodal input and text output.

A fine-tuned multimodal model based on unsloth/Llama-3.2-11B-Vision-Instruct, optimized for vision-language tasks and enhanced instruction-following capabilities, achieving 2x training acceleration through the Unsloth framework

Quantized version of EraX-VL-7B-V1.5, supporting Vietnamese, English, and Chinese, suitable for tasks like insurance and OCR.

Donut model fine-tuned on ZhTrainTicket for document image-to-text conversion without OCR processing.

Donut is an OCR-free document understanding Transformer model composed of a visual encoder (Swin Transformer) and a text decoder (BART), capable of directly extracting text information from images.