# Low-Precision Optimization

This is a text-to-video generation model. After GGUF conversion, it can be used in compatibility with ComfyUI-GGUF.

This is a GGUF format conversion version of a text-to-video generation model, aiming to provide a more efficient model usage experience.

Light-R1-14B-DS is a 14B-parameter quantized large language model supporting text generation tasks, designed for efficient inference in resource-constrained environments.

INT4 quantized version of FLUX.1-Canny-dev, capable of generating images based on text descriptions while adhering to the Canny edges of the input image.

A text-to-image conversion model implemented based on the gguf library, supporting multiple quantization types and suitable for image generation tasks.

PaliGemma is a lightweight vision-language model developed by Google, combining image understanding and text generation capabilities, supporting multilingual tasks.