Video Super-Resolution with Text-to-Video Model

Colorize grayscale images using automatic captions

Add a logo to anything

Demo for https://github.com/Byaidu/PDFMathTranslate

Generate application code with Qwen2.5-Coder-32B

Generate text responses using images and text prompts

Consistency generation of portrait and subject

Create 3D mesh by chatting.

Upload documents for Q&A

Kolors Character to keep character developed with Flux

Kolors Portrait to keep face identity developed with Flux

Chat with a Qwen AI assistant

Generate code for applications based on descriptions

Track your online presence with reverse face search

Vote on AI responses to rank models

Blind Image Restoration with Instant Generative Reference

Spanish finetune for the original F5 model.

Upgraded to v1.0!

An end-to-end (e2e) Voice Language Model by Fish Audio.

Prompt with Images in flux[dev]