Convly
Upload an image to generate prompts, style analysis, and model parameters
About Convly
Convly's Image-to-Prompt Generator accepts PNG, JPG, or WEBP images, analyzes them, and reverse-generates text-to-image prompts, style breakdowns, and suggested parameters for Midjourney and Stable Diffusion. It also handles photos, screenshots, and hand-drawn work to help recreate lighting, composition, or color style; generated seeds and settings are estimates and cannot recover the original data in the final image.
Best for
Best use cases
Extract text-to-image prompts from a reference image
Recreate an image's lighting, composition, or color style
Turn a real photo into a text-to-image prompt
Generate starting parameters for Midjourney or Stable Diffusion
Features
Image reverse prompting
Analyze an uploaded image and generate reusable text-to-image prompts.
Style breakdown
Break down the image's visual style to help approximate the original look.
Platform parameter suggestions
Provide suggested parameters for Midjourney and Stable Diffusion.
Multi-format image upload
Support PNG, JPG, and WEBP; maximum 6 MB per image.
Pros
- Completely free
- No registration required
- No watermark
- No daily limit for normal use
Cons
- Cannot recover the final image's original prompts, seed, or exact settings; parameters are estimates
- Upload size limit: 6 MB
Pricing Plans
Free
- No registration required
- No watermark
- No daily limit for normal use
* Pricing information is for reference only. Please refer to the latest announcement on Convly's official website.