Alibaba instruction-based image editor
Qwen Image Edit follows plain instructions on a single upload: rewrite signs and menus in English or Chinese, recolor garments, or swap objects while the surrounding layout stays put. 3 credits per edit on RenderFlow AI.
Your generated image will appear here.
Enter a prompt and click 'Generate' — or start from an example:
Examples
Drag the handle to compare each source and result. The chalkboard, tea poster, and coat pairs lead the gallery: each after frame is a real Qwen Image Edit result, and each before frame is the source that edit started from.
text in image
Prompt: Change the header from "MORNING MENU" to "EVENING MENU" in the same decorative chalk capitals. In the left column, change "Matcha Latte 5" to "Ginger Tea 4.5"; keep the hand-lettered chalk style and dark green board.
Before: source menu generated for the edit pair. After: real Qwen Image Edit output (wavespeed-ai/qwen-image/edit).
bilingual text
Prompt: Change the vertical Chinese text from 茉莉花开 to 冬日茉莉, keeping the calligraphy style, vertical layout, and position unchanged. Keep the English headline, gaiwan, blossoms, and celadon palette.
Before: source poster for bilingual text edit. After: real Qwen Image Edit bilingual text change.
semantic recolor
Prompt: Change the oversized trench coat from crimson to deep emerald green satin with a subtle sheen, keeping the fabric drape, wind-blown movement, folds, and dramatic side light. Keep the model and concrete parking structure unchanged.
Before: source fashion still. After: real Qwen Image Edit semantic recolor.
text in image
Prompt: Change the header from "MORNING MENU" to "EVENING MENU" in the same decorative chalk capitals. In the left column, change "Matcha Latte 5" to "Ginger Tea 4.5"; in the right column, change "Seasonal Galette 6" to "Mushroom Toast 7". Keep the hand-lettered chalk style, the dark green board, the small illustrations, and the two-column layout exactly the same.
text in image, bilingual
Prompt: 把竖排的中文"茉莉花开"改成"冬日茉莉",保持书法字体、排版方向和位置不变。英文标题、盖碗、茉莉花和青瓷色调保持原样。 (Change the vertical Chinese text from "茉莉花开" to "冬日茉莉", keeping the calligraphy style, vertical layout, and position unchanged. Keep the English headline, the gaiwan, the blossoms, and the celadon palette as they are.)
semantic edits
Prompt: Change the oversized trench coat from crimson to deep emerald green satin with a subtle sheen, keeping the fabric's drape, the wind-blown movement, the folds, and the dramatic side light exactly the same. Keep the model, the concrete parking structure, the shadows, and the muted gray environment unchanged.
controlled changes
Prompt: Change step 2's text from "STEEP 12 hours" to "STEEP 16 hours" in the same type style, and change the small icon in step 2 from a clock to a crescent moon. Keep all other steps, numbers, cards, icons, connecting lines, colors, and the cold brew bottle illustration exactly the same.
text in image
Prompt: Change the curved text along the top of the ring from "CEDAR RIDGE" to "PINE HOLLOW" and the bottom text from "EST. 1974" to "EST. 1968", keeping the same distressed two-color screen-print lettering and the curve of each line. Keep the bear silhouette, the pine trees, the mountain peaks, the double-ring border, and the small stars exactly the same.
text in image + layout
Prompt: Change the masthead from "GRID" to "FRAME" in the same bold grotesque type, and change the cover line "THE NEW MINIMALISM" to "THE QUIET LAYOUT" in the same small aligned type. Keep the dancer photo, the yellow fabric, the concrete wall, the other cover lines, and the overall grid and hierarchy exactly the same.
Qwen Image Edit is the instruction-based editor from Alibaba’s Qwen Image line. It is known for bilingual text edits and layout-aware changes from a sentence rather than masks (Hugging Face model card).
On RenderFlow AI the canvas takes one image, an instruction, an output format (JPEG, PNG, or WebP), and a seed. Each edit costs 3 credits. This page does not add a second reference image or a custom width and height. Those controls are on Qwen Image Edit Plus at 4 credits. To design a new poster or menu instead of editing one, use the Qwen Image generator.
The canvas takes one image. Choose the frame whose layout you want to keep. There is no mask step before the edit.
Write one change, and put any text that must appear in quotes: "change the sign to read '营业中 OPEN'" or "swap the red mug for a glass teapot." English, Chinese, or both can sit in the same instruction.
Say where the change is — top line, left column, on the coat — and name what stays, such as "keep the logo bar and the two-column layout."
Choose JPEG for photos, PNG for graphics you will keep editing, or WebP for the web. The seed defaults to -1, a fresh result. Set a specific seed when a direction is right and the next try should stay close.
One image and a sentence belong here at 3 credits. When you need a second or third reference, or width and height from 256 to 1536 pixels, move the same instruction to Qwen Image Edit Plus at 4 credits.
Both editors run in the browser on RenderFlow AI. Stay on this page for one image. Open Qwen Image Edit Plus when the job needs extra references or an exact pixel size.
| Feature | Qwen Image Edit | Qwen Image Edit Plus |
|---|---|---|
| Credits | 3 per image | 4 per image |
| Inputs | 1 image | Up to 3 images |
| Output size | No width or height control | Width and height, 256–1536 px (default 1024×1024) |
| Formats | JPEG, PNG, WebP | JPEG, PNG, WebP |
| Seed | Yes, default −1 | Yes, default −1 |
| Use it for | Single-image text, object, and color edits | Packaging, label references, and exact output sizes |
Alibaba also publishes a Qwen-Image-Edit-2509 checkpoint. RenderFlow does not label this 3-credit canvas as that release. New artwork, rather than an edit, starts on the Qwen Image generator.
Yes. Quote the exact characters and name the line to change. The surrounding layout stays put when the instruction says what must stay, such as the calligraphy position, the English headline, or the two-column menu.
Use one direct command: change this copy, swap this object, or recolor this garment. Put the required words in quotes, in English, Chinese, or both. Position words such as "top line" or "left column" make the edit easier to place. The before-and-after cards on this page are working prompts.
JPEG, PNG, and WebP. JPEG suits photographic edits, PNG suits graphics you will keep editing, and WebP suits images headed to the web. The control on the canvas is labeled Output Format.
The instruction usually left out what must stay. Add an anchor such as "keep the logo, footer, and two-column layout; change only the headline." There is no mask on this canvas, so the sentence is the boundary.
For one image and a sentence, especially text in English or Chinese, yes. It costs 3 credits per edit. Use Qwen Image Edit Plus when you need more than one input or an exact pixel size. SeedEdit V3 is the closer first try for simple photo cleanup, and Nano Banana Edit fits jobs that remix up to ten reference images.
Open the editor on this page, upload one image, write the instruction, choose JPEG, PNG, or WebP, and generate. RenderFlow runs the model in the browser, so you do not need an Alibaba API key. A seed of -1 is a new result; set a specific seed when the next try should stay close.
On this page, yes: you upload one image and get one edited image back. The canvas does not generate a picture from text alone. New posters and menus start on the Qwen Image generator instead.
No. This page runs the RenderFlow model alibaba/qwen-image-edit, the 3-credit single-image editor. RenderFlow does not label that endpoint as the Qwen-Image-Edit-2509 checkpoint.
RenderFlow does not label alibaba/qwen-image-edit as the latest release. Alibaba publishes other edit checkpoints, including Qwen-Image-Edit-2509. This page is the 3-credit single-image editor, not a promise of the newest checkpoint.
RenderFlow does not publish a separate Qwen block list on this page. The Terms of Service forbid uploading or submitting material that is illegal, hateful, harmful, obscene, or sexually explicit, and they forbid unlawful use of the service. This page does not offer NSFW generation or a control that turns a filter off.
Alibaba publishes the Qwen-Image-Edit model card on Hugging Face. RenderFlow does not ship those weights or a local installer. On this site you run the editor in the browser for 3 credits per edit.
Upload one image, describe the change in a sentence, and generate for 3 credits. For extra references or an exact pixel size, use Qwen Image Edit Plus instead.
Open in AI Image EditorUse advanced Alibaba Qwen image editing for product and layout changes.
Create images with strong text rendering and layout control.
Edit photos with ByteDance SeedEdit V3 prompt-based image editing.
Edit images with ByteDance Seedream V4 Edit.
Edit existing images with Google Nano Banana Edit.
Create controllable 720p or 1080p AI videos from text prompts with Alibaba Wan 2.7.