AI Generator
Images & videos from text. Powered by AI.
Prompt
▼
Tip Use Enhance to add lighting, camera, style & detail automatically.
Reference Image
None
▼
Upload a style or reference image. Only compatible models will be shown.
AI Model
GPT Image 1 • 1 💎
▼
Choose your image model. Premium = more detail.
Negative Prompt
▼
Click to add presets:
Size
Square • 1:1
▼
Style Boosters
0
▼
Tap to add flavor.
None selected
Image → Prompt
FREE
▼
Upload an image or paste URL to reverse-engineer a prompt.
Video Mode
▼
Choose how to create your video.
AI Model
MiniMax • 3 💎
▼
Higher quality = more credits.
Video Prompt
▼
Tip Describe motion, camera, atmosphere.
End Frame (optional)
None
▼
Upload an image showing where the video should end. Only compatible models (Kling 2.6, Veo 3.1) will be shown.
Source Image
▼
Upload the image to animate.
Or paste URL
Tip Describe motion & camera movement.
End Frame (optional)
None
▼
Upload an image showing the final frame. The AI will animate from your source to this end point.
Motion Reference
▼
Upload a reference video (dance/action) and a character image. The AI will make your character perform the same movements.
📹 Reference Video (3-30s)
Or paste URL
Video preview
🧍 Character Image
Or paste URL
Image preview
Duration & Ratio
YouTube • 16:9
▼
Duration
Aspect ratio
Narration
Off
▼
AI Studio: Any photo becomes a talking avatar. Upload selfies, illustrations, AI portraits — no limits.
Script
▼
Write what the avatar should say.
0/
Avatar
Select avatar
▼
Choose a preset avatar or upload your own image.
Loading avatars…
Voice
Select voice
▼
Loading voices…
Or use your own voice:
Background
Color
▼
Choose what appears behind your avatar.
Pick a background color
Background Music
None
▼
Add subtle background music to your avatar video.
— or —
Music Volume
25%
Settings
▼
Speed
1.0x
Video Size
Resolution (AI Studio only)
Topic & Source
▼
Video Style
▼
Nova
Presenter & Captions
▼
💬 Caption Style
🎬 Video Style Template
Auto will pick the best template based on your content.
🎵 Background Music
Uses local tracks from
music/ folder first, then Freesound API, then synthesized fallback. Script Preview
▼
Click "Write Script" to generate a storyboard.
Cost 1 credit per scene image + free voiceover & assembly
Text to Speech
▼
0 / 5,000 characters
Nova
Speed:
🐢
🐇
1.0×
Info Uses OpenAI TTS-1 or ElevenLabs depending on selected voice
My Voices (Clone)
▼
No cloned voices yet.
🎤 Clone a New Voice
Upload 30s–3min of clear audio (no background noise). Your voice will be available across all tabs.
Output
Ready when you are.
No output yet
Generate something wild.
History
▼