Editing your images
Edit an image with an editing model: put it in the reference slot, say what should change and what should stay, keep the aspect ratio and combine several images.
What this video covers
To edit an image in LUVI, you use an editing model: you give it your image, describe what should change, and the model makes a new version of it.
Models with "Edit" in their name are built for this. Here, we're using Nano Banana 2 Edit.
When you pick an editing model, image slots open in the Reference section, and at least one image is required.
The quickest way in is to right-click the image in your library and choose Use as Reference. You can also drag it in or upload it from your computer.
Once the image is in, the warning turns green and the price appears; it isn't worked out until a reference is added.
In the prompt, say what should change, and spell out what should stay the same. Here, we're giving the dog a little party hat and a bow tie, and keeping the dog and the park exactly as they are.
Watch the aspect ratio: the edit comes out in whatever ratio is selected. If your image is portrait, pick the same ratio, here 3:4.
Press Generate. The result lands in your library as a new file, and your original stays untouched.
You can combine images, too: put another one in the second slot. Nano Banana 2 Edit takes up to fourteen images, and the counter in the Reference heading keeps track.
Type an at sign in the prompt and the images in the slots are listed; pick one to refer to it by name.
Here, we ask it to sit the dog from the first image on the sofa in the second, keeping the dog looking exactly the same.
In short: choose an Edit model, put your image in the slot, say what changes and what stays, and check the ratio.
More from Going further
All tutorials
1:31Tutorial 15aYour first workflow
Build your first chain in Workflow: add nodes, pick models, wire an image into a video, check the price and run it.
1:50Tutorial 15bBatch generation in Workflow
Run one line with many inputs using Batch, Dice and Stack, and see how each one affects the price.
1:49Tutorial 15cWorkflow operators
Shape the text before it reaches the Generator with the Merge, Caption, Style and Pose operators.
1:49Tutorial 15dManaging workflow runs
The Preflight Check, running part of a graph, groups, cancelling, saving workflows and the panels on the right of the canvas.
1:24Tutorial 16aAI voice-over
Turn text into speech in LUVI: pick a voice-over model and a voice, set the stability and language, and generate.
1:26Tutorial 16bAI music
Make background music, or a full song with your own lyrics, in LUVI with MiniMax Music 2.6.
1:06Tutorial 16cTranscribing audio
Turn a recording into text with xAI STT v1, with speaker labels and filler words when you need them.
2:06Tutorial 17Talking avatars and lip sync
Make a portrait talk from an image and an audio file, or give an existing video a new voice with lip-sync models.
1:23Tutorial 18aGenerating 3D models
Turn an image or a description into a 3D model with Hunyuan 3D or HI3D, and see how extra views and parameters shape the result.
1:17Tutorial 18bThe 3D viewer and downloads
Inspect your 3D model in the viewer with lenses, lighting, wireframe and texture views, then download it as a GLB.