Visit Sogni.ai

Mixing two reference images

Mix visual ideas from two reference images into one coherent output.

Kontext lets you blend visual ideas from two reference images into a single, cohesive result—guided by a simple prompt. Whether you're combining the style of one image with the subject of another, placing an object into a new setting, or merging two characters into a shared scene, Kontext understands both images and follows your instructions to create something new. It's a powerful way to explore visual storytelling, remix ideas, or build consistent scenes without needing advanced tools or technical steps.

Examples

Prompt: "Place the flower in the vase"

Prompt: "She is holding the bottle"
Prompt: "She is now in the new setting"

Prompt: "The wizard and the monster are working together on the computer, coffee" Style: "Film: Lomo"

Prompt: "Make the wizard in the style of the colored image"

Prompt: "Add the text to the back of her jacket"

Prompt: "Her white top is now colorful with a design"

Need help? Ask in our Discord!

For any questions regarding the use of Sogni, tips, suggestions, bugs, sharing art, discussing AI and life, or simply hanging out... Join our Discord community! Join Sogni Discord ✨

PreviousKontextNextKontext-Fill

Last updated

Was this helpful?