Edits that keep the character
Changes poses, expressions or clothing without losing recognizable character features.
Change part of a picture
Modify consistent characters while preserving their core identity. Edit poses, expressions, or clothing without losing recognizable character features
Opens the image studio with Ideogram V3 Character Edit ready to use. You can look around as a guest. Running it takes the Pro plan or higher.


What it makes
Change part of a picture
Repaints only the area you mark and leaves the rest alone.
What you need
What you get
The picture with the marked area repainted
Ideogram V3 Character Edit changes part of an image while keeping a character recognizable. You supply the image, a mask over the part to change, a prompt and a character reference image. It is made for edits to poses, expressions or clothing, and it returns an edited image.
Four inputs are required: a prompt, an image, a mask image and a character reference image. The image and the mask must have exactly the same width and height. The reference file can be JPEG, PNG or WebP, up to 10MB in total. The model uses only one. Rendering Speed (Turbo, Balanced or Quality), Color Palette and Expand Prompt are optional. Color Palette sets the colors, as a preset name or as color codes. Style Codes are 8-character codes that stand for a look. Expand Prompt switches MagicPrompt on or off. Style reference images and a mask for the character reference are optional too.
Ideogram V3 Character Edit costs 1000 credits per run. Ideogram V3 Edit costs 300 credits, needs no character reference and has a Style Preset option. Ideogram V2 Edit Text to Image costs 800 credits. Ideogram V2 Turbo Edit Text to Image costs 500 credits.
Same job: change part of a picture. Compare before you choose.
Transform existing images with Ideogram V2's editing capabilities. Modify, adjust, and refine images while maintaining high fidelity and realistic outputs with precise prompt control.
FLUX.1 [pro] Fill Fine-tuned is a high-performance endpoint for the FLUX.1 [pro] model with a fine-tuned LoRA that enables rapid transformation of existing images, delivering high-quality style transfers and image modifications with the core FLUX capabilities.
The GenFill Route enables the generation of objects by prompt in a specific region of an image. You can define the area for object generation by using a mask that outlines the region where the object will be created. Our model is optimized to work seamlessly with blob-shaped masks.
Bria GenFill enables high-quality object addition or visual transformation. Trained exclusively on licensed data for safe and risk-free commercial use. Access the model's source code and weights: https://bria.ai/contact-us
Changes poses, expressions or clothing without losing recognizable character features.
A mask image marks the part to change, and your prompt fills it. The mask must match the image size exactly.
Upload the image to edit and a mask over the part to change. Keep both the same size.
Upload one image of your character, then write a prompt for what should fill the masked part.
Run the model for 1000 credits and look at the edited image.
Change a character's pose or expression while the character stays recognizable.
Mask the clothing and describe a new outfit in your prompt.
Quick answers to help you get the most out of Ideogram V3 Character Edit in FunAI Studio.