Super OCRs Demo
Experiment with small super OCR models here.
Experiment with small super OCR models here.
Generate realistic audio from video and text
Generate edited images based on prompts and input images
Compare Qwen-VL models for object detection.
generate a video from an image with a text prompt
Edit and guide image generation
Easily remove your videos background!
The most opinionated, anime-themed SDXL model
User Friendly Image & Video Upscaler!
High-fidelity Text-To-Speech
Enhance and upscale images with advanced controls
Qwen3-VL / Qwen2.5-VL Demo
Apply the motion of a video on a portrait
Launch a customizable user interface
Generate text from an image and question
Detect, segment, classify objects in images and videos
Realtime implementation of Whisper large turbo
Remove/Change background of video.
99+ Impressive LoRA's For Flux.1
Blind Image Restoration with Instant Generative Reference
Upscale and enhance images
Generate person images with new clothes or poses
Generate responses using images and text input
VGGT (CVPR 2025)