IDEFICS2 Playground
Chat with a visual AI that answers questions about images
Chat with a visual AI that answers questions about images
Generate images from prompts and templates
Video Editing
Relight photos with custom lighting using AI prompts
Generate realistic speech and sounds from any text
Enhance and restore old photos and AI-generated faces
Transfer portrait styles to images and videos
Segment images into objects, instances, or scenes
Generate 3D views from a single image
Edit images using text instructions
Train LoRAs with Ease
Upload an image and edit it using segmentation, inpainting, or regeneration
Generate photorealistic portrait videos from audio and a photo
Generate text from images and prompts
Edit a photo to match a new text description
Generate OpenPose-filtered video from input video
Video Dubbing with Open Source Projects
Describe what you want, AI writes the FFMPEG command
Create video ads from product names
Generate AI images featuring your own face
Real-Time Image Generation with SDXL Lightning
Clone a voice to speak your custom text
Generate images from text, existing images, or by inpainting
Generate edited images using edge, pose, and other guides
Generate cartoon video interpolating between two images
Generate stunning high quality illusion artwork
Generate artwork from sketches with AI
Transcribe or translate audio and YouTube videos to text
Fast one-step tiled restoration with VOSR 2.0
4M: Massively Multimodal Masked Modeling
Generate a short video from an uploaded image
Generate photorealistic images from text prompts
Generate images from photos or text with enhanced prompts
Stable Diffusion 3 with text2img and img2img
Create interactive videos from images with drag-and-draw controls
Advanced Image Generator
Upscale and enhance images with AI-powered tile control
Generate personalized images that keep your face identity
Inpaint images with custom prompts
Gradio demo of CharacterGen (SIGGRAPH 2024)
Edit images using text prompts and masks
DALLE 4K | A RealVisXL_V3, V4 | HI-Res Images Gen.
Generate 360° panoramas from text prompts
Generate videos from text prompts
Generate personalized portraits of a specific person from photos
Create images from text and reference photos
Remove image background and get transparent PNG
Clarity AI Upscaler Reproduction
Generate a video animating a source image to match a given audio
Audio-based Lip Sync for Talking Head Video Editing
Merge two videos and check GPU/NVENC status
Create images of a given character in different poses
Edit image regions using a reference picture
Create a video using aligned poses from an image and a dance video
Analyze human behaviors from videos
Generate subtitles and translate audio files
Create virtual outfits by combining images
Notify users that the Object Eraser tool is retired
Audio-Driven Portrait Animations
Generate normal maps from images and videos
Stunning images using stable diffusion.
Vocal and background audio separator
Stunning images using stable diffusion.
Generate animated videos from text and image prompts
Edit images with predefined styles or text prompts
Generate images from text prompts with FLUX.1-schnell
Generate a 3D mesh from a single image
Generate object masks from an image with point guidance
Launch a web UI for interacting with the model
Fast Text 2 Video Generator
Teleport objects into new backgrounds using masks
Aesthetically Controllable Text-Driven Stylization w/o Train
Easily remove your videos background!
Turn an image into a motion video
Text-to-Video
Animate Your Pictures With Stable VIdeo DIffusion
Try on clothes virtually on a photo using diffusion models
Generate text based on an image and prompt
Generate a 3D model from a single image
Discover the Finegrain Camera with a single click
Text-to-Video
Quickly edit the expression of a face
Flux-Labs with LoRA
Add a logo to anything
Text-to-3D and Image-to-3D Generation
Generate new images from a subject photo and text prompt
Automatically discover creative knowledge inside diffusion
Fast image relighting using Latent Bridge Matching
Create images in the style of a reference picture
Generate high-resolution images with prompts and masks
Generate 3D video from input images
Generate 3D character models from single images
Convert images of humans to biomechanically accurate 3D skeletons
Transcribe audio files into written text
Enhance facial features in images using a reference face
Infinite-Length Film Generation
Enhance image resolution up to 8x