Ideogram 4
Ideogram 4 state of the art open weights
Ideogram 4 state of the art open weights
Generate 3D models from a single image
Chat with a multimodal AI using text and images, audio, or video
8B CSM-style text-to-speech with voice cloning
Generate natural speech from your written text
Generate speech from text with optional voice cloning
Play notes to steer real-time music (PyTorch)
PaddleOCR-VL-1.6_Online_Demo
Generate 3D models from a single image
State-of-the-art image generation, in your browser.
Detect and label objects in images and videos
generate a video from an image with a text prompt
Ideogram 4 state of the art open weights
Demo of the Collection of Qwen Image Edit LoRAs
Image edit, text to image, image upscale, remove watermark
text to video, image to video, video extend
Generate vivid images from text prompts in seconds
FireRed-Image-Edit Γ Qwen-Image-Edit-Rapid (Transformers)
VoxCPM2 Nano-vLLM Demo
High-quality voice cloning TTS for 600+ languages
NVIDIA Cosmos3-Nano β text/image to video + audio
generate a video from an image with a text prompt
Audio-driven talking-head video generation (Meituan LongCat)
Run Bonsai-Image-4B models on GPU
Dense video captions and timestamp search
Generate full HTML web apps from text prompts
Generate videos from text, images, audio, or video clips
High-fidelity 3D Generation from images
Chat with an AI assistant using the LFM2.5 model
Demo of the Collection of Qwen Image Editing LoRAs
Training-free reference-guided generation with FLUX.2-klein
Operators over the three Epicure ingredient embeddings