Image Generation

Generate pictures of your companion in the scenes you describe. Your prompt is the text that tells the image generator what to create.

Three ways to start

You can ask for a photo right in the chat, or open the full generator for more control.

The camera icon in Messages view

Tap the camera icon in the message bar, then choose Image.

For your first photo, try Send me a photo of... with:

You sitting at a café table, wearing a blue sweater, with morning light through the window.

In a group chat, name the companion you want:

Sophia: send me a photo of you at the bar.

Photos with more than one companion require the V3 Model.

The Generate button in messages view

Open the chat panel, go to the Gallery tab, and tap Generate. This opens the full generator directly.

The Generate tab in the sidebar

Tap Generate in the navigation menu. This opens the generator with a gallery of your past images.

Using the generator

The full generator lets you choose the companions, scene, and image settings. For your first companion image, choose Nectar Companion Model and one companion.

💡

The numbers on the screenshot match the eight steps below. Some fields change with your selected model.

1. Type

Choose Image.

2. Model

Model selects the image model you want to use. Choose Nectar Companion Model to generate an image of a selected companion.

Other options include Anime, Realistic, and Experimental Realistic.

If you need beta access, submit a support ticket in our Discord.

Image models are separate from the chat models that write replies. “Ultimate” in an image model’s name is not your subscription plan.

Your choice also affects how you write the prompt. See Writing better prompts below.

3. Companions

Choose who appears in the picture. You can select up to 10 companions for a V3 image.

Check the selection even when you open the generator from a chat.

1. Tap the Companions field.

2. Use Discover to find public companions or Saved to find your bookmarks and likes.

3. Select the companions you want.

4. Remove anyone with the X on their chip.

5. Tap Accept.

Start with one companion while you learn the generator. For group images, use the example that you’ll see farther down this page.

4. Model Version

After choosing a companion, select one of the Model Version options shown in your account.

These are versions of the companion image model, not separate visual styles.

V3 and V3 2K give you the most detail and the most control over the scene. Use one of these for the steps on this page.

Your plan also includes an image allowance. Your account shows which versions it covers and the price of each paid generation.

5. Prompt

Describe the companion’s clothes, action, surroundings, and lighting by typing in the text box.

Mika sits at a café table in a blue sweater, holding a white coffee mug. Morning light comes through the window. Waist-up view.

💡

Enhance expands a rough idea into a full prompt. Check its displayed price before using it. Read the result before tapping Create.

Under the box, suggestion chips are grouped into Outfits and Scene. Under Show more, you can also find Body and Face.

Tap a chip to add it to your prompt. Tap Generate new ideas for a fresh set of suggestions.

6. Icks

Icks describes what you want left out of the image. This is also called a negative prompt.

For example:

text, watermark

Keep this consistent with your main prompt. If you ask for a red coat, do not also exclude red.

The field appears on supported options, including the Realistic and Companion V2 models. It does not appear on the Companion V3 model.

7. Customizations

Customizations are ready-made tiles for faces, outfits, poses, and effects. Available categories depend on the model.

Choose up to three per image. Keep your selections consistent with your prompt.

See Customizations.

8. Create

Review your companions, prompt, and settings. Check the displayed price before a paid generation, then tap Create.

To refine the result, change one detail and generate again.

Writing better prompts

Start with the details that matter most to your picture. Add detail where you want control.

💡

Prompt Architect, in the Community tab, can help you draft image and video prompts. Review the prompt before using it.

Each model requires different prompts

Before you try this: Generate one image and note the Model and Model Version that you used.

💡

Power tip: On Experimental Realistic, weights and BREAK give you the most control. Save a plain-language baseline first, then compare one syntax change at a time.

Use these formats as starting points:

💡

Power tip: Change one thing at a time. If you change the prompt and model together, you will not know which change helped.

Getting a better shot

Give the scene a specific place, light source, and action.

Less specific:

standing, looking at the viewer, simple background, soft daylight

More specific:

leaning on a wooden counter in late window light

Name the style. Try live-action, anime, oil paint, comic, or 1970s print.

Adding Weights in your prompt

Power tip

Before you try this: Start with a working prompt on the Base or Companion V2 model.

A weight increases or reduces the emphasis on a phrase. Use it to refine one detail, such as a scarf that you want to stand out.

The V3 model does not use weights. Describe the detail in plain sentences instead.

How to write a weight

Put the phrase in parentheses, followed by a colon and a number:

(red scarf:1.3)

Weights guide the result. They do not guarantee that an item appears or disappears.

Starting numbers

For the Companion V2 model, use these as starting ranges:

Change one weight by 0.1 at a time and compare the result.

High weights can distort details. Keep most of the prompt unweighted.

V3 model works differently

Before you try this: Choose Nectar Companion Model under Model, select your companion, then choose V3 or V3 2K under Model Version.

💡

Power tip: Before changing a Companion V3 setup, save a baseline image and compare one appearance change at a time.

Write in plain sentences, as if you are describing a photo to a friend. Weights and BREAK do not work on the V3 model.

See Adding weights for supported options.

Short prompt: V3 picks the details

Keep the prompt short when you want V3 to choose some of the details.

Mika on a stone rooftop at night. Choose her outfit and pose. Full moon and city lights.

This sets the scene while leaving the outfit and pose open.

Detailed prompt: V3 follows your description

When you want a specific result, describe:

1. Shot or style.

2. Who is in the picture.

3. Clothes.

4. Action or pose.

5. Place and lighting.

6. Viewpoint.

Mika stands on a stone rooftop at night in a shiny black latex catsuit, looking at the viewer. Full moon, city lights. Wide shot.

Describe visible actions. “She leans on the railing and laughs” gives clearer direction than “she feels carefree.”

For group images, give each companion a separate description. See Multiple companions.

Changing a companion’s outfit

Ask for the new outfit in chat and describe it explicitly.

In the full generator, use the prompt for the scene, lighting, and pose. A detail you add to Additional Physical Traits will show up in new images, but removing one does not take it back out, so ask in chat when you want a different outfit.

Multiple companions

Before you try this: Generate a single-companion image first. Choose Nectar Companion Model under Model, then select V3 under Model Version and the companions for your group image.

You can include up to 10 companions. They do not have to be yours. Use Discover in the companion picker to add public companions to the scene.

One companion, one paragraph. Start each paragraph with the name exactly as it appears on the companion’s card. Then describe their clothes, action, and position.

Start with a scene header:

[Shot type or style] in [place], [light]. [Total] people only.

For example, with Sophia, Kirie, and Mika selected:

Wide night shot of a motel parking lot, neon reflected on wet asphalt. Three adults only.

Sophia
Leather jacket and jeans. Standing beside the open driver's door of a parked sedan on the left.

Kirie
White tank top and a gold chain. Standing beside the motel entrance in the center.

Mika
Shorts and a loose shirt. Standing in the foreground on the right, looking toward Kirie.

Give everyone a distinct position before adding complex interactions.

If you want a clearer composition, simplify the scene or start with fewer companions.

Troubleshooting

Try one adjustment at a time.

For clothing, replace a vague instruction:

describe the body, then mention an outfit

With a direct description:

wearing a blue sweater covering the torso and full-length jeans, fully clothed

Generating in the background

Images generate in the background while you chat and browse.

• Pro: Up to two images at once.

• Ultimate: Up to four images at once.

What you can do with a generated image

• Turn it into a video. Use the video button on the image. See Video Generation.

• Make it the profile picture. Open the image and choose Submit as profile picture.

• Add it to the gallery. Review the destination and visibility options before featuring it.

• Let it set the mood. Your chat background changes to your most recent generated image.

• Attach it to a greeting. Use Greeting Media in the companion editor.

• Save it to a folder. Organize images into collections you can return to from Saved Items.