Segment objects in images and videos using text prompts

Generate chat responses using Llama-2 13B model

Generate images using selected LoRAs and prompts

Create high-quality HD cutouts with just a text prompt

Build datasets using natural language

FLUX 4-bit Quantization(just 8GB VRAM)

Engage in chat with Llama-2 7B model

Generate speech from text

Convert your image to a line drawing

Remove background from images

Describe images using multiple models

Create and edit images using DDPM and SEGA techniques

Fast, efficient, & multilingual text-to-speech

Chat with an AI that understands text and images

Edit images using text prompts and concepts

Enhance image resolution up to 8 times

Spanish finetune for the original F5 model.

Generate responses and perform tasks using AI

Chat with a Qwen AI assistant

a tiny vision language model