Sora 2
OpenAI's Sora 2, text to video with audio.
None defined yet.
OpenAI's Sora 2, text to video with audio.
Reference for ByteDance Seedream 4.0 image model
ByteDance's image model. Text to image, up to 4K.
Edit an existing image with a written instruction.
The updated Seedream checkpoint from ByteDance.
Unedited sample output from ByteDance Seedance 1.0
Reference for Qwen-Image, Alibaba's open text-to-image model
Reference for Qwen-Image-Edit, instruction-based editing
Google's Nano Banana Pro, text to image.
Instruction-driven editing with Nano Banana Pro.
Higher-resolution editing with Nano Banana Pro.
Drive a portrait from an audio track โ lip sync and head...
Image editing built on HiDream-I1.
One prompt, three models, side by side.
MiniMax Hailuo 2.3, image to video, speed-optimised.
Bria's FIBO editing model, trained on licensed data.
Extend an image beyond its original frame (outpainting).