Image to Prompt
The Image to Prompt feature converts images into text prompts, showing how AI interprets the image and providing a reference structure that can be easily modified to generate custom images.
Click the Image to Prompt button in the Prompt section to run the feature.
![]() | Supported AI Tools | |
Image Creation | V | |
Image Editing | -- | |
Video Creation | V | |
Video Editing | -- | |
3D to Image | V | |
3D to Video | -- | |
Create Actor | -- | |
For 3D Guided Gen
Converts a 3D viewport image into a prompt and enables further editing to include details like facial expressions, pose, lighting, rendering style, and emphasis.
| Image Input - 3D Viewport | AI Output |
![]() | ![]() |
| Image to Prompt | Prompt Editing |
cartoon boy with spiky orange hair and round black glasses, wearing green and black striped t-shirt, white socks, blue sneakers, raising right fist triumphantly while seated at a worn wooden school desk, cartoon girl with brown braided hair and red-framed glasses, wearing pink sleeveless top and white knee-high socks, head down on desk in exhaustion, third character bald with brown hair tuft, face-down asleep on desk behind girl, all seated on blue plastic school chairs, dark studio background with soft spotlighting, mood of playful exhaustion and classroom chaos, warm skin tones, vibrant clothing colors contrasted against muted desk textures, ultra-detailed 3D render, 8K resolution, cinematic lighting, subsurface scattering on skin, realistic fabric wrinkles, depth of field with shallow focus on foreground characters, volumetric ambient occlusion, Pixar-style character design, high dynamic range, photorealistic textures | cartoon boy with spiky orange hair and round black glasses, wearing green and black striped t-shirt, white socks, blue sneakers, raising right fist triumphantly while seated at a worn wooden school desk, smiling with determination, cartoon girl with brown braided hair and red-framed glasses, wearing pink sleeveless top and white knee-high socks, searching for content in the book, third character bald with brown hair tuft, face-down asleep on desk behind girl, all seated on blue plastic school chairs, mood of playful exhaustion and classroom chaos, [light: Window Light] warm skin tones, vibrant clothing colors contrasted against muted desk textures, ultra-detailed 3D render, 8K resolution, cinematic lighting, subsurface scattering on skin, realistic fabric wrinkles, depth of field with shallow focus on foreground characters, volumetric ambient occlusion, Pixar-style character design, [style: 3D Cartoon] emphasizes finely detailed individual hair strands, high dynamic range, photorealistic textures |
For Image Gen
Converts a custom image (.png, .jpg, .jpeg, or webp) into a prompt that can be refined with adjustments to character appearance, scene details, and lighting.
| Image Input | AI Output |
![]() | ![]() |
| Image to Prompt | Prompt Editing |
Tyrannosaurus rex, scaly green and gray skin with battle scars, roaring with mouth wide open revealing sharp teeth and pink tongue, lunging forward aggressively toward a dusty forest road, military-style olive green jeep speeding away with visible driver and passenger, dense prehistoric forest with towering moss-covered trees and sunbeams piercing through canopy, chaotic and adrenaline-fueled mood, dynamic motion blur on jeep and dust clouds, rich earthy greens, browns, and golden sunlight highlights, ultra-detailed cinematic rendering, 8K resolution, HDR lighting, photorealistic textures, volumetric fog, depth of field focus on T-rex, high contrast shadows and highlights, dramatic action composition | Dilophosaurus, scaly skin with battle scars, roaring with mouth wide open revealing sharp teeth and pink tongue, lunging forward aggressively toward a dusty forest road, military-style olive green Military ATV speeding away with visible driver and passenger, dense prehistoric forest with towering moss-covered trees and sunbeams piercing through canopy, chaotic and adrenaline-fueled mood, dynamic motion blur on Military ATV and dust clouds, rich earthy greens, browns, and golden sunlight highlights, ultra-detailed cinematic rendering, 8K resolution, HDR lighting, photorealistic textures, volumetric fog, depth of field focus on Dilophosaurus, high contrast shadows and highlights, dramatic action composition |
For Video Gen
Converts the provided start and end frame images into a prompt, then decomposes it into multiple shots describing key moments across different time frames of a video clip.
| Image Input - Start Frame | Image Input - End Frame | AI Output |
![]() | ![]() | ![]() |
| Image to Prompt | ||
An elderly couple rides bicycles along a sunlit dirt path through lush green fields, smiling and glancing at each other; camera pans from side view to front-facing as they pedal forward, houses in the distance growing clearer, capturing joyful movement and rural tranquility under a soft blue sky. | ||
| Prompt Editing | ||
[Overall camera style]: The camera moves in a handheld style with subtle natural shake and organic motion, creating a cinematic sense of presence and immediacy. Motion is dynamic and realistic, yet readable and controlled—no extreme jitter, chaotic framing, or sudden jumps. | ||







