Features
Text-to-image generation from natural-language prompts
High prompt fidelity with long, structured prompts
Sharp details, crisp edges, natural tones, coherent lighting
Adjustable inference steps (1-50) and guidance scale (0-20)
Negative prompting to exclude unwanted content
Multiple aspect ratios: 1:1, 3:4, 9:16, 4:3, 16:9
Output formats: JPEG, PNG
Account history to review past generations
Fast iteration with live progress preview
Credit-based usage (4 credits per image)
API for programmatic generation
Prompt patterns for portraits, products, and scenes (Pro and above)
Priority processing and support (paid plans)
Future access to new model workflows (Pro and above)
Browser-based, no GPU required
Image to Video with first/last frame control
Reference to Video with up to 7 images
AI Sound Effect Generator (auto audio from video)
AI Image Generator (text-to-image)
Anime Art to Video with fluid motion
Story Grid for multi-shot coherent productions
Templates for viral content (kissing, hugging, etc.)
My References: save characters, props, scenes
Vidu Claw for marketing content creation
Unlimited free generation in Off-Peak Mode
10-second video generation speed
Mobile video creation workflow
API platform for enterprise integration
Vertical video support for TikTok/Reels
