AI Image Generator
Models
Nano

Google's cutting-edge image generation model

3 credits
Fast
High Quality
Gpt

OpenAI's GPT-4o image generation model

3 credits
High Quality
Text & Image
Seedream

ByteDance image generation and reference-based editing in 2K, 3K, or 4K

6 credits
2K/3K/4K
Text & Image
Flux

Flux Kontext standard model with balanced performance

4 credits
Fast
High Quality

GPT Image 2.5 Flare

0/20000
Public Visibility

When this option is enabled, the output image may be selected by AI Generate and published to the Explore.

Required Credits
3
Notification
This is a notification message
Sample Images
GPT Image 2.5 Flare · Lovart ME

GPT Image 2.5 Flare AI Image Generator & Editor Text and image inputs · 1K / 2K / 4K

Use the Flare workflow to generate an image from text or edit up to 16 references. Choose 1K, 2K or 4K output and an opaque, transparent or automatic background. A result costs 3, 10 or 16 credits respectively.

1
AI Image Generator & Editor
Text and image inputs
16
Reference images
Use a clean source image and describe the protected details, requested changes and final composition.
3 / 10 / 16
Credits
1K: 3 · 2K: 10 · 4K: 16
2
Text and image inputs
Create in Lovart ME, then review the result in your history.

What you can make · GPT Image 2.5 Flare

Create in Lovart ME, then review the result in your history.

Product assets with background control

Use an opaque background for a composed scene or transparent output for an asset you plan to place in another layout. Inspect the resulting edges before delivery.

Editing with distinct reference roles

Upload up to 16 references, but explain what each contributes. Keep product identity, material, visual style and layout references separate in the prompt.

Resolution and ratio together

All 13 aspect options are available at 1K. The 27:16, 16:27, 9:8 and 8:9 ratios are limited to 1K; choose another ratio before switching to 2K or 4K.

Prepare a useful first draft

Start at 1K to inspect composition, reference roles and edit boundaries. Choose a higher resolution when the brief and destination format are settled.

Set the output before generating

1K costs 3 credits, 2K costs 10 credits and 4K costs 16 credits per image. 27:16, 16:27, 9:8 and 8:9 are available at 1K only. Choose opaque, transparent or auto background; every job returns one image.

Resolution

1K / 2K / 4K

Credits

1K: 3 · 2K: 10 · 4K: 16 Credits

Aspect ratios

auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9

Aspect ratios

01

Aspect ratios

auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9

02

Reference images

16 · Use a clean source image and describe the protected details, requested changes and final composition.

GPT Image 2.5 Flare · Prompts for practical production tasks

Use a clean source image and describe the protected details, requested changes and final composition.

Transparent product asset

Adapt the subject, setting and protected details to your own brief.

Prompt Isolate the ceramic lamp from reference 1 on a transparent background. Preserve its shape, glaze color and visible texture. Show the full lamp without cropping. Do not add a floor, text or accessories.

Working note Use a clean source image and describe the protected details, requested changes and final composition.

Catalog scene

Adapt the subject, setting and protected details to your own brief.

Prompt Create a 4:3 catalog photograph of a linen backpack on a pale wood bench. Soft daylight, accurate stitching and natural fabric folds. Keep the product centered and leave the background simple. No text.

Working note Use a clean source image and describe the protected details, requested changes and final composition.

Reference edit

Adapt the subject, setting and protected details to your own brief.

Prompt Edit reference 1. Keep the camera angle and product geometry. Use reference 2 only as a material guide for the surface. Match the original shadows and do not change the label or introduce new objects.

Working note Use a clean source image and describe the protected details, requested changes and final composition.

How to use GPT Image 2.5 Flare

Create in Lovart ME, then review the result in your history.

  1. 01

    Text and image inputs

    Use text for a new scene. Upload references only when they provide useful visual direction.

  2. 02

    Describe the subject and what must stay fixed

    State the action or edit, composition and lighting. Give each reference one role.

  3. 03

    Set output and review the displayed price

    Choose a supported resolution, aspect ratio and background where available. Review the displayed price before submitting.

  4. 04

    Generate, inspect and revise

    Inspect details and continuity, then change one or two instructions per attempt. Your job remains available in history.

GPT Image 2.5 Flare · Questions before you generate

Create in Lovart ME, then review the result in your history.

What can I create with GPT Image 2.5 Flare?

Use the Flare workflow to generate an image from text or edit up to 16 references. Choose 1K, 2K or 4K output and an opaque, transparent or automatic background. A result costs 3, 10 or 16 credits respectively.

Which output settings are available?

Resolution: 1K / 2K / 4K. Aspect ratios: auto, 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 27:16, 16:27, 9:8, 8:9.

How is the price calculated?

1K costs 3 credits, 2K costs 10 credits and 4K costs 16 credits per image. 27:16, 16:27, 9:8 and 8:9 are available at 1K only. Choose opaque, transparent or auto background; every job returns one image.

What should reference uploads contain?

Upload up to 16 clear images. Describe which subject, material, palette or composition each reference should guide and which details must stay unchanged.

How long does generation take?

Generation has no fixed completion time. Queue load, output settings and upstream availability affect the wait.

Compare settings and prices in the other model workbench.