Professional image generation and editing platform powered by Alibaba Tongyi's Z-Image series models
AI video generator: turn photos into video, make lip-sync and music videos with AI models like Seedance 2.5 and Kling
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
$10 trial (1,000 credits, one-time per account); monthly plans: Starter $25, Creator $75, Pro $149; 1 credit = $0.01; video prices: Seedance 2.5 at 160 credits ($1.60) for 5 seconds in 720p and 412 credits ($4.12) in 1080p; Kling 4.0 at 145 credits ($1.45) in 720p and 215 credits ($2.15) in 1080p; W
Key features
Text-to-image generation
Image-to-image editing with natural language instructions
Bilingual Chinese and English text rendering
Sub-second latency generation with Z-Image-Turbo
6 billion parameter efficient model architecture
Photorealistic image generation
Commercial use license
No watermark output
Access to prompts gallery
Photo to video conversion with multiple AI models (Seedance 2.5, Kling 4.0, Wan 3.0)
Music video generation with lip-sync to lyrics
Video generation with sound included
Control over first and last frames for animation
Multiple resolutions (480p, 720p, 1080p) and video lengths (4-30 seconds)
Image generation in 1K and 2K resolutions
Subtitles and logo overlay on videos
Storyboarding and shot planning tools
Video editing tools (trim, extract frame, upscale)
Exact pricing displayed before generation
What makes it different
Supports both Chinese and English text rendering for multilingual image generation
Sub-second image generation speed with Z-Image-Turbo
Precise instruction-guided image editing based on natural language
Open-source Z-Image-Base model available for fine-tuning and custom development
Multiple model variants for different use cases and performance needs
Transparent pricing: users see exact cost before pressing generate
One credit balance works across all AI models and features
Purchased credits never expire
Multiple professional video models integrated in one workspace