Help-center page for AI Image, updated Nov 9, 2026
This page is Genspark's help-center guide to AI Image, a picture generator and editor that turns a prompt or a reference image into one picture. It says it was updated Nov 9, 2026. The rest of the page is explanatory help text, so the cards describe what the page says about the product, its billing and its limits rather than a separately titled contract.
Supporting quotations
Learn how to use Genspark AI Image, a picture generator and editor that turns a prompt or a reference image into one polished picture.
Updated Nov 9, 2026
Qualifications & exceptions
The date shown is an update date for the page; the page does not label it an effective date for any rule.
Not stated here
The page does not say whether it forms part of Genspark's Terms or is help content only.
The page does not say which countries or regions it covers.
Use & Processing · Company practice
AI Image makes or edits one picture from a prompt or reference image
You describe what you want, optionally attach a reference image and pick a model. AI Image returns one, two or four pictures depending on the count you set, and each chat is saved as a project so you can come back and keep editing. It does not build boards, decks, pages or videos; for bigger jobs another product takes over. The page adds that some older pages call the product the "AI Image Agent" and says they mean this product.
Supporting quotations
AI Image makes or edits one picture from a prompt or a reference image.
AI Image returns one, two or four pictures, depending on the count you set. Each chat is saved as a project, so you can come back and keep editing.
It doesn't build boards, decks, pages or videos.
Some older pages call it the "AI Image Agent". They mean this product.
Qualifications & exceptions
The count you set decides whether one, two or four pictures come back.
The scope is one picture per job; boards, decks, pages and videos belong to other products.
Not stated here
The page does not say how long a saved project is kept.
Use & Processing · Context
Start-page controls: model button, Setting, Auto Style, Camera, Auto Prompt
The start page has a model button that lists every image model with a price level and a multiplier on each row, a Setting button for image size, quality, aspect ratio and how many images to make, and Auto Style, Camera and Auto Prompt buttons. The page describes these three as shaping the picture "without changing your words", yet its navigation table describes the Auto Prompt toggle as letting the product rewrite your prompt, and a later section says Auto Prompt rewrites your prompt before it goes to the model. The page does not reconcile the two descriptions.
Supporting quotations
A model button that lists every image model, with a price level and a multiplier on each row.
A Setting button for image size, quality, aspect ratio and how many images to make.
Auto Style, Camera and Auto Prompt buttons that shape the picture without changing your words.
Let the product rewrite your prompt
Qualifications & exceptions
The model button, Setting and the style tools are described for the start page; the app has fewer controls (see the app card).
Not stated here
The page does not say whether the Auto Prompt rewrite is shown to you.
The model picker lists every image model; models are added and retired over time
The model button lists every image model. The first row is Auto-select Models, described as "Auto-select the best models for your tasks". Each row shows the model's name, a price level from $ to $$$$ and a multiplier that compares its cost with the base model. Everyone sees the same models and only billing differs by plan. Models are added and retired over time, so the picker is the list to trust, and the label under each result names the model that made it.
Supporting quotations
The model button above the prompt box lists every image model. The first row is Auto-select Models, described as "Auto-select the best models for your tasks".
Every row shows the model's name, a price level from $ to $$$$ and a multiplier such as "2×" that compares its cost with the base model.
Everyone sees the same models. Only billing differs by plan.
Models are added and retired over time, so the picker is the list to trust. The label under each result names the model that made it.
Qualifications & exceptions
Everyone sees the same models; only billing differs by plan.
Not stated here
The page does not say how Auto-select Models chooses a model or whether the model it picks can bill credits.
Use & Processing · Context
Setting shows only the controls the model supports; some sizes and qualities bill credits
Setting holds the controls the selected model supports, and each section shows only if the model has it. Image Size runs from Auto and 0.5K to 4K, Quality from Auto and Low to Extra High or Max, depending on the model, and aspect ratio from Auto Size to ratios such as 1:1, 16:9 and 21:9. Generation count is 1, 2 or 4 pictures per prompt. On Plus and Pro from September 18, 2026, a Credits badge marks any size or quality option that bills credits.
Supporting quotations
Setting holds the controls the selected model supports. Each section shows only if the model has it.
Image Size Auto, 0.5K, 1K, 2K, 3K or 4K, depending on the model
Quality Auto, Low, Medium, High, Extra High or Max, depending on the model
Aspect Ratio Auto Size, plus the ratios the model offers, from 1:1, 16:9 and 9:16 to 21:9 and 9:21
On Plus and Pro from September 18, 2026, a Credits badge marks any size or quality option that bills credits.
Qualifications & exceptions
The options depend on the selected model.
The Credits badge is described for Plus and Pro from September 18, 2026.
Ratio rules: the closest ratio is used if the model lacks yours, yet a set ratio is said to be "always honored"
The page says a model that lacks the ratio you chose uses the closest ratio with the same orientation. In the same paragraph it says a ratio you set is always honored. It does not explain how both can hold when the model does not offer the ratio you set. It also says models that only edit offer Auto and nothing else, and that with the ratio on Auto an edit follows the proportions of the reference image.
Supporting quotations
A model that has no ratio you chose uses the closest ratio with the same orientation.
A ratio you set is always honored.
Models that only edit offer Auto and nothing else. With the ratio on Auto, an edit follows the proportions of the reference image.
Qualifications & exceptions
Models that only edit offer Auto and nothing else.
With the ratio on Auto, an edit follows the reference image's proportions.
Not stated here
The page does not say how a ratio you set can always be honored when the model offers no such ratio and the closest one is used instead.
Auto Prompt rewrites your prompt before it goes to the model; there is no negative prompt
Auto Prompt is a toggle that rewrites your prompt before it goes to the model. Auto Style opens a picker of looks, and Camera turns on camera controls. There is no negative prompt; to keep something out of a picture, you say so in the prompt, for example "no text". Saved prompt presets add a Using preset button. Earlier the page describes these style tools as shaping the picture "without changing your words", which sits uneasily with a rewrite of your prompt.
Supporting quotations
Auto Prompt is a toggle that rewrites your prompt before it goes to the model.
Auto Style opens a picker with Search styles... and Filter by category.
Camera turns on camera controls: Camera, Lens, Focal Length and Aperture.
There's no negative prompt. To keep something out of a picture, say so in the prompt, for example "no text".
Not stated here
The page does not say whether you see the rewritten prompt or what changes the rewrite makes.
Cross-references
contrast (model-proposed): Start-page controls: model button, Setting, Auto Style, Camera, Auto Prompt — The start-page description says Auto Prompt shapes the picture without changing your words, while a later section says Auto Prompt rewrites your prompt before it goes to the model. The page does not reconcile the two.
Use & Processing · Context
Result toolbar and side editor; four named edit tools are on the Plus and Pro free list from September 18, 2026
Every result has a hover toolbar with Recreate (runs the same model again), Remix (attaches the image as a reference) and Image to Video (opens AI Video in a new tab). Clicking a result opens a side editor with Draw to Edit, Remove Background, Erase, Expand, Image Unblur, Image to Video, an info panel and Download image. Four edit tools with the same price are on the free list for Plus and Pro from September 18, 2026: eraser, fill, outpaint and object removal.
Supporting quotations
Every result has a toolbar on hover.
Recreate runs the same model again.
Remix attaches the image to the prompt box as a reference, so your next prompt builds on it.
Image to Video opens AI Video in a new tab.
Draw to Edit lets you brush an area and describe the change.
Remove Background cuts the subject out.
Erase removes what you brush.
Expand extends the picture past its edges.
Image Unblur sharpens and enlarges an image.
An info panel shows the prompt, the model and the style.
Download image saves the picture, and Back to Gallery returns to the results.
Four edit tools with the same price are on the free list for Plus and Pro from September 18, 2026: eraser, fill, outpaint and object removal.
Qualifications & exceptions
The free-list statement applies to Plus and Pro from September 18, 2026.
Not stated here
The page does not map the four named free tools to the side-editor tools, or say whether Recreate, Remix, Image to Video or the other edit tools bill credits.
AI Video is a separate product whose billing is not described here.
Use & Processing · Restriction or exception
Reference images: 100 MB per file and 80 images per conversation
You can attach any image type with the attach control. Each file can be up to 100 MB and a conversation holds up to 80 images; over the size limit the chat shows a size-limit message and past the image limit it reads that a maximum of 80 images is allowed. How many references one model uses at once depends on the model, so the page says not to count on a fixed number.
Supporting quotations
Attach any image type with the attach control. Each file can be up to 100 MB, and a conversation holds up to 80 images.
A file over the size limit shows "{fileType} size limit is {maxSize}MB". Past the image limit the chat reads "Maximum 80 images allowed in total conversation".
How many references one model uses at once depends on the model, so don't count on a fixed number.
Qualifications & exceptions
The reference count that is used depends on the model.
Not stated here
The page does not define 'any image type' or list supported formats, and does not say how attached images are kept.
Use & Processing · Company practice
Download image is the save path; there is no Save to AI Drive, Save to Notion or Copy button
Download image in the side editor is the save path. There is no Save to AI Drive, Save to Notion or Copy button on an AI Image reply. To use a picture in another product you download it and attach it there; the one direct handoff is Image to Video. A later recipe repeats that there is no Save to AI Drive or share button.
Supporting quotations
Download image in the side editor is the save path. There's no Save to AI Drive, Save to Notion or Copy button on an AI Image reply. To use a picture in another product, download it and attach it there. The one direct handoff is Image to Video.
there's no Save to AI Drive or share button on an AI Image reply, so download the picture to keep it.
Use & Processing · Context
AI Image only makes or edits one picture; bigger jobs go to other products by download and attach
AI Image makes or edits one picture. When the job needs a board, a deck, a page or a clip, another product takes it, and there is no button from AI Image to most of them, so the handoff is a download and an attach. AI Chat reads images and never makes them. Starting from a preset page opens the same AI Image with a prompt filled in, while logo, menu, thumbnail and mockup pages open Genspark Design.
Supporting quotations
AI Image makes or edits one picture. When the job needs a board, a deck, a page or a clip, another product takes it. There's no button from AI Image to most of them, so the handoff is a download and an attach.
It reads images and never makes them
Starting from a preset page, such as a headshot, anime or photo-editor page, opens the same AI Image with a prompt filled in. Logo, menu, thumbnail and mockup pages open Genspark Design.
Not stated here
Billing and limits of the other products named (Media Studio, Genspark Design, Super Agent, AI Slides, AI Video, AI Chat) are on their own pages, not supplied here.
Use & Processing · Company practice
A prompt or input that fails a content filter is blocked and not charged
If a prompt or input fails a content filter, the chat shows a message such as "NSFW content detected. No credits were charged. Please avoid NSFW content." Failed and blocked images are not charged, and you change the prompt or the reference image and try again.
Supporting quotations
If a prompt or input fails a content filter, the chat shows a message such as "NSFW content detected. No credits were charged. Please avoid NSFW content." Failed and blocked images aren't charged. Change the prompt or the reference image and try again.
Not stated here
The page does not say what the content filter covers beyond the NSFW example, whether blocked prompts are logged, or whether repeated blocks affect an account.
Use & Processing · Procedure
Wrong size or ratio: Auto lets the model choose; a model without your ratio uses the closest one
Auto lets the model choose size and ratio, so you open Setting and set them. Not every model offers every size or ratio, so a model without your ratio uses the closest one with the same orientation, and an edit with the ratio on Auto follows the reference image. This section does not repeat that a set ratio is always honored.
Supporting quotations
Open Setting and check that Image Size and Aspect Ratio are set, because Auto lets the model choose. Not every model offers every size or ratio, so a model without your ratio uses the closest one with the same orientation. An edit with the ratio on Auto follows the reference image.
Use & Processing · Procedure
If a model is retired, pick another and run the prompt again
The picker changes as models are added and retired, and the label under each image shows the model that made it. If a model you used is gone, you pick another and run the prompt again. The page links an explanation of why models are removed.
Supporting quotations
The picker changes as models are added and retired.
If a model you used is gone, pick another and run the prompt again.
Not stated here
The linked explanation of model retirements is not supplied here.
Use & Processing · Company practice
FAQ: AI Chat reads images and never makes them
You cannot make images in AI Chat. AI Chat reads images and never makes them, and pictures are made in AI Image.
Supporting quotations
No. AI Chat reads images and never makes them. Make pictures in AI Image.
Use & Processing · Procedure
Reference photos of a person: the page says nothing about permission or retention
The recipe for keeping a face or character consistent has you attach one clear photo of the person or character with the attach control and prompt to keep the face, hairstyle and pose in a new scene. The page gives usage steps only.
Supporting quotations
For: a new scene with the same person or character.
Attach the photo with the attach control.
Not stated here
The page does not say whether permission from the person pictured is needed, how attached photos are retained or used, or whether faces are treated differently.
Use & Processing · Procedure
Download image to keep a picture, then attach the downloaded file in another product
To find an earlier picture you open the chat list or Recents, open the chat, click the picture and choose Download image. To use it in another product you attach the downloaded file there.
Supporting quotations
Click the picture and choose Download image.
To use it in another product, attach the downloaded file there.
You get: the file on your device.
Use & Processing · Procedure
Image to Video opens AI Video in a new tab where the clip is finished
Choosing Image to Video on a picture, or in the side editor, opens AI Video in a new tab and you finish the clip there.
Supporting quotations
Hover the picture and choose Image to Video, or choose it in the side editor.
AI Video opens in a new tab.
Finish the clip there.
Not stated here
AI Video's billing, limits and terms are not described on this page.