EditorNodesPricingBlog

AI IMAGE GENERATOR

Seven ways to make an image

Generate from a prompt, edit a picture you already have, keep a character consistent across a sequence, upscale for delivery, cut out a background, train the system on your own style, or sketch an idea and let it finish. All of it runs in the browser.

Open the image workspace

One workspace, one type dropdown

The image workspace is a single surface with a generation type dropdown at the top. You pick the type, the form below rebuilds itself with the controls that type needs, and you generate. Switching from Text to Image to Image Enhance changes the whole form rather than sending you to a different page.

The form also changes with the model. Two models under the same generation type can expose different controls, because a negative prompt, a seed field or a custom dimension input only appears where the model supports it. This is worth knowing before you plan a workflow around a specific setting.

Results from every type land in the same place. The Artifact Gallery on the My Creations page holds them, and any completed result can be picked as the input to a later generation, which is what makes chaining these tools practical.

The seven generation types

Each one has its own page covering the models it offers, the settings it exposes and what it is actually good at.

Text to Image

Write a prompt and generate images from scratch. Pick the model, aspect ratio and output format, and add a LoRA style if you have one.

Image to Image

Start from an image you already have and describe the change. Useful for style transfer, edits and mood changes on an existing frame.

Character Generation

Upload one to three reference photos and keep the same character consistent across many generations.

Image Upscaling

Increase resolution on an existing image while keeping identity and detail intact, with a selectable upscale factor.

Background Remover

Cut the background out of an image with edge detection precise enough for compositing work.

Model Training

Train a custom FLUX LoRA on your own images so you can generate in your own style or with a specific subject.

Draw to Edit

Sketch an idea on the built in canvas, add a prompt, and turn the drawing into a finished image.

A working sequence

Most finished work passes through more than one of these tools. A typical run starts in Text to Image to establish framing and lighting across a small batch. The strongest frame then moves to Image to Image, where the prompt describes only the change rather than the whole picture again.

If the same person needs to appear in several frames, Character Generation replaces the first step. One to three reference photos hold the identity stable while the prompt varies the outfit, pose and setting.

Delivery is the last pass. Background Remover isolates the subject when it needs to sit over something else, and Image Upscaling raises resolution once the composition is settled. Upscaling early wastes credits on frames you are going to discard.

Model tutorials on the blog

Longer coverage of individual models, including behaviour the product pages do not have room for.

Seedream 5.0 Pro image generation

Walkthrough of the Seedream 5.0 family, including where the Lite variant fits.

Nano Banana 2 Lite

The default model in the image workspace, covering prompt handling and speed.

FLUX.2 image generation guide

How the FLUX.2 family behaves on prompt adherence, detail and text rendering.

MidJourney 8.0

Prompt structure and stylistic control for MidJourney style generation.

AI character generation

Keeping a face and identity stable across a whole sequence of shots.

BEN2 background removal

Edge quality on hair and semi transparent areas, and where it breaks down.

Common questions

What is the difference between the seven image tools?

Text to Image builds an image from a written description alone. Image to Image starts from a picture you supply and changes it. Character Generation keeps one person consistent across many images. Image Upscaling raises resolution. Background Remover cuts the subject out. Model Training teaches the system your own style. Draw to Edit turns a rough sketch into a finished frame.

No. Every generation type runs in the browser, so there is no local install, no GPU requirement and no model download. You sign in and generate from the image workspace.

Models that support batch output let you set the number of images in the form, commonly one to four per run. Generating a small batch is the fastest way to compare framing and lighting before committing to a direction.

Each generation uses credits. The exact cost appears in the form before you submit and changes with the model, the number of images and, for upscaling, the upscale factor. If a generation fails it is refunded automatically during credit reconciliation.

Yes, and most production work does. A common sequence is generating a base frame with Text to Image, adjusting it with Image to Image, removing the background, then upscaling the result for delivery. Image to Image can pick any of your previous completed tasks as its source.

Results appear in the Artifact Gallery on the My Creations page, reachable from the Creations menu on the right side of the workspace. You can download each result from its Artifact card, and everything is also written to your cloud storage folder.

Commercial use depends on the licence of the model you generated with, which differs across the roster. Check the terms and conditions and the individual model coverage on the blog before publishing work from any single model.

    © 2026 - AI FILMS LLC