PuLID-FLUX
Generate images from text prompts and ID images
Generate images from text prompts and ID images
Kontext multi image composition on FLUX[dev]
Generate, edit, or understand images using text prompts
Generate images from text prompts
Use NVIDIA H100 GPU
Upscale and enhance images with Real-ESRGAN
Clone voices using text and audio samples
olmocr / nanonets ocr / rolmocr / qwen2vl ocr / aya vision
Easily expand image boundaries
Audio Conditioned LipSync with Latent Diffusion Models
Conversational speech generation
Fast image relighting using Latent Bridge Matching
Turn images into videos with prompts
monkey ocr / nanonets ocr / smoldocling / typhoon ocr
Generate images from text prompts
Generate audio for a video using captions and descriptions
A demo space for HomeDiffusionModel
Qwen Text to Image with LORA support
Use AI to Change Clothing
Generate audio from text using a reference audio sample
Video Dubbing with Open Source Projects
Generate depth maps from images
Transcribe audio files to text with timestamps
Generate relit images from your photo