Above the clouds — light, wool and wind

Image-to-image editing

Same scene. A new direction.

An emerald jacket becomes ivory. Then the warm theatre light becomes cool blue. Compare each edit with its actual source, using the slider or your keyboard.

Before the curtain — original scene
Change the wardrobe
SourceEdit

Prompt & settings

Change the wardrobe

  • Seedream 5.5
  • Edit
  • 2K
  • 16:9
  • JPEG
  • Price in Create

Image prompt (English)

Edit the provided photograph. Change only the actress's emerald-green jacket into an ivory silk tailored jacket, preserving its fitted silhouette and believable folds. Keep the same woman, face, hair, expression, hands, pose, framing, theatre curtains, background people and lighting. Preserve everything outside the jacket as closely as possible. Return one cohesive photographic frame.

Each request uses one reference: original → wardrobe edit → lighting edit. Inspect the face, hands, curtains and framing; details can still change.

Text in an image

Put your words in the world.

A theatre entrance, a passing character and a short message inside the scene. Give the text a surface, a position and a reason to be there.

One night only — text in the scene

One night only — text in the scene

Seedream 5.5 · Generation · 2K · 16:9 · JPEG

Prompt & settings

One night only — text in the scene

  • Seedream 5.5
  • Generation
  • 2K
  • 16:9
  • JPEG
  • Price in Create

Image prompt (English)

A widescreen live-action film still outside a small independent cinema on a dry late-summer evening. Two fictional adults in their thirties hurry laughing through the illuminated entrance, one holding the door for the other. Above them, a real physical cinema marquee is readable and nearly front-facing. Its large main line reads exactly "THE LAST LIGHT"; its smaller second line reads exactly "ONE NIGHT ONLY". These are the only prominent words. The lettering belongs to the illuminated marquee, with convincing perspective and material. Warm tungsten bulbs, fading lavender sky, deep red facade, animated gestures and a few adult passers-by. A bold but natural film composition with human energy and tactile photographic detail. No added poster overlay, no standalone objects.

The prompt requests “ONE NIGHT ONLY”. This selected image shows the result; check every letter before publishing.

Cinematic image generation

Look closer. Stay human.

A runner catches her breath. Examine the skin, flyaway hair and textured fabric in this close portrait, then open the original at full size.

Open original ↗

After the race — skin and fabric detail

Seedream 5.5 · Generation · 2K · 3:4 · JPEG

Prompt & settings

After the race — skin and fabric detail

  • Seedream 5.5
  • Generation
  • 2K
  • 3:4
  • JPEG
  • Price in Create

Image prompt (English)

A close, emotionally alive portrait from an independent sports film. A fictional Black woman runner around thirty has just finished a coastal race; she is catching her breath and laughing toward a friend outside the frame. Sunlight grazes the tiny beads of sweat and natural texture on her cheek, salt air lifts short curls, and a cobalt technical running shirt shows fine woven fibres and lived-in creases. Her hand loosely holds the edge of her collar, with natural anatomy. Warm late-afternoon rim light, the soft sea and other adult runners in the background, restrained shallow depth of field. Honest skin, small imperfections, subtle film grain, exuberant but unposed. A vertical 3:4 photographic frame, no text or graphic overlay.

Face & hair — After the race — skin and fabric detail
Detail from the same imageNo retouching

This selected result illustrates one portrait brief. Inspect facial details and anatomy before using any generated image.

Native transparent PNG

Free to move. Ready to compose.

Generate an isolated subject with a real alpha channel. Change the preview background to inspect the edges, then open the unchanged original PNG.

Free to move — native transparent PNG

Prompt & settings

Free to move — native transparent PNG

  • Seedream 5.5
  • Generation
  • 2K
  • 3:4
  • PNG
  • Price in Create

Image prompt (English)

A full-body cinematic photographic portrait of a fictional adult contemporary dancer caught in a powerful turning step, one foot grounded and the other extended, both hands naturally separated from the torso. A flowing deep-red chiffon outer layer arcs around an opaque black performance costume, with fine translucent fabric edges and a few loose strands of hair. Convincing anatomy, expressive face, clean directional film lighting with subtle warm highlights, tactile fabric and natural skin. Entire figure and flowing fabric comfortably inside the vertical frame. Native transparent background with real alpha, including delicate hair and chiffon transparency; no environment, floor, shadow backdrop, checkerboard pattern, lettering or graphic overlay. Let the pose and fabric movement be artistically expressive.

The dancer is the same image on every background. Transparency was verified in this original and its WebP display copy; no background-removal effect is applied here.

Prompt guide

How to prompt Seedream 5.5

Describe the action, framing and light. Put exact text in quotes. Use the example below, or shape your idea with Milo.

MAKE YOUR MOVE — a cinematic street campaign

MAKE YOUR MOVE — a cinematic street campaign

Seedream 5.5 · Generation · 2K · 16:9 · JPEG

Prompt & settings

MAKE YOUR MOVE — a cinematic street campaign

  • Seedream 5.5
  • Generation
  • 2K
  • 16:9
  • JPEG
  • Price in Create

Image prompt (English)

A compelling live-action feature-film still, 16:9 widescreen. A fictional woman in her late twenties in a deep burgundy trench coat has just emerged from a Parisian metro stairway into a rain-soaked street at blue hour. She is caught mid-stride, turning toward someone just outside the frame, alert and full of intent; her face is clearly visible, her coat moves in the wind. Several adults cross the street behind her; a passing taxi adds a soft streak of warm light. A large physically printed illuminated advertising panel, nearly front-facing on the right side of the street, reads exactly "MAKE YOUR MOVE" in three beautifully spaced lines of bold off-white sans-serif capitals. These are the only prominent words. The panel belongs naturally to the real location. Reflections on wet pavement, cinematic cyan and amber practical lighting, natural skin texture, believable hands, coherent perspective, rich deep blacks with detail. Shot on a 40mm anamorphic lens, restrained film grain, subtle halation, sophisticated campaign-film composition. The woman and the sign remain comfortably inside the central 80 percent of the image. A real human story in progress, evocative and dynamic, not a posed stock photograph. A single cohesive photograph with no borders or added graphic overlay.

Subject & action
Give the subject one clear action and a readable gaze.
Frame the moment
Choose the aspect ratio, camera distance and where each subject sits.
Light & texture
Name the light source, its direction and the textures you want to see.
Give text a surface
Quote exact words and specify their surface, position and line breaks.

The idea behind this image

A woman in a burgundy coat emerges from a Paris metro at blue hour. She turns towards someone outside the frame. Rain catches cyan and amber light. An illuminated street poster reads “MAKE YOUR MOVE”.

Shortened for clarity. Use or copy the complete original prompt below the image.
Prompt writing tips

Guide each reference

Say which image defines the person, clothing or location. Use up to 10 reference images to guide one output.

Continue from the last edit

Use the previous result as the next reference. Name what must stay, then ask for one change. For an opaque scene, keep Background set to Opaque.

Choose a transparent output

Select PNG and Transparent in Create. Describe the isolated subject and leave space around its edges. JPEG cannot preserve transparency.

  • Check every letter, face and hand in the result before using it.
  • For a video starting frame, keep a readable pose and leave room for motion. Seedream creates the still; animate it in a separate video generation.
Official model guide ↗

Seedream 5.5 — Specifications

Formats, settings and limits to check before creating.

The last train — two characters under the rain

The last train — two characters under the rain

Seedream 5.5 · Generation · 2K · 16:9 · JPEG

Prompt & settings

The last train — two characters under the rain

  • Seedream 5.5
  • Generation
  • 2K
  • 16:9
  • JPEG
  • Price in Create

Image prompt (English)

A cinematic live-action film still, 16:9 widescreen, from a beautifully photographed contemporary drama. On an almost empty covered railway platform at night, a fictional woman around thirty wearing a forest-green jacket reaches back to take the hand of a fictional man around thirty-five in a dark wool coat. They are both walking toward a waiting train; she turns toward him with a small spontaneous smile, while he looks at her with concern and affection. Their faces and connected hands are readable and anatomically natural. Warm light spills from the open train door behind them into the cool blue rain beyond the platform roof. A station worker and two adult travellers remain small in the background, adding scale and a believable lived-in setting. The image catches a real transition, coat hems moving and one foot just leaving the ground. Strong foreground, middle ground and background separation, glistening pavement, delicate steam in the distance, fine natural skin texture and wool detail. 50mm cinema lens, softly rolled highlights, subtle film grain, realistic color separation, intimate and emotionally charged without melodrama. Carefully composed with both people fully legible and room around them for a later camera move. One cohesive physical location, a film frame rather than a fashion pose, no title or graphic overlay.

Seedream 5.5 — Specifications — In MaxVideoAI
SettingIn MaxVideoAI
Text-to-ImageSupported
Image-to-ImageSupported
Resolution options1K / 1.5K / 2K
Aspect ratiosauto / 1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 3:2 / 2:3 / 21:9
Output formatJPEG / PNG
Reference imagesUp to 10
Images per request1
BackgroundAuto · Opaque · Transparent (PNG)

Settings available in Create. The table describes MaxVideoAI’s implementation of this model. Source: MaxVideoAI

Hero prompt & settings

Above the clouds — light, wool and wind

  • Seedream 5.5
  • Generation
  • 2K
  • 16:9
  • JPEG
  • Price in Create

Image prompt (English)

A cinematic live-action adventure film still, 16:9. A fictional adult woman in her early thirties pauses halfway through a mountain hike, turning toward someone just outside the frame with a quietly amazed expression. Medium close shot from chest up, her face slightly right of center, wearing a charcoal weatherproof jacket and an ivory chunky wool scarf. Her raised hand lightly grips the scarf near her collarbone, with natural anatomy. Fine flyaway dark hair caught in the mountain wind, natural freckles and skin pores, individual woven wool fibres and the weathered jacket texture clearly resolved. Cool alpine peaks and low cloud in the distance, late afternoon sunlight breaking through a cloud and catching her face and the scarf from the side. Human and spontaneous, not a fashion pose. Restrained blue-grey and cream palette, warm natural skin, luminous soft highlights, realistic optical depth, high detail on face, hand and scarf, gentle background falloff. Frame the full head with breathing room and a useful amount of surrounding landscape, no tight crop. One cohesive photographic scene from a film, no text, no title, no border, no collage, no inset, no skin smoothing or over-sharpening.

Generated and reviewed on 13–14 November 2026 with Seedream 5.5 via BytePlus. All people and scenes are AI-generated. The edit sequence uses the previous image as its single reference.

Model by ByteDance

FAQ

A few things to know.

What is Seedream 5.5, and what can I create?

Seedream 5.5 is an AI image generation and editing model developed by ByteDance. On MaxVideoAI, use text or up to 10 reference images to create portraits, cinematic scenes, campaign images and transparent PNG assets. Each request returns one still image.

How is Seedream 5.5 different from Seedream 5.0 Pro?

ByteDance presents 5.5 as an advance in successive edits, realism and text rendering, with native transparent PNG output. In MaxVideoAI, 5.5 also offers 1K, 1.5K and 2K instead of Pro’s 2K-only output. Both accept up to 10 references and return one image per request. The examples above show selected results, not a controlled head-to-head benchmark.

How do I refine the same scene?

Use the selected image as a reference. State what to preserve and ask for a focused change, then inspect the new result before using it for the next edit.

Can I create a transparent background?

Yes. Choose PNG output and the transparent-background setting. JPEG is suitable for an opaque scene.

Which resolutions and formats are available?

MaxVideoAI offers 1K, 1.5K and 2K, with JPEG or PNG output. Image editing accepts up to 10 references and returns one image; use Lite when you need image sets.

Can I animate the image afterwards?

Save the still and choose a video model for a separate generation. A readable silhouette, clear hands and space around the subject make the opening frame easier to plan.

How much does Seedream 5.5 cost on MaxVideoAI?

MaxVideoAI uses pay-as-you-go credits, with no required subscription. Choose your resolution and references in Create, then review the current price before generating. Each new generation or edit has its own quote.

Limits & practical advice
  • One generated image per request
  • Choose PNG and a transparent background for an image with an alpha channel.
  • Review rendered text and fine details before publishing.
Responsible image creation
  • Use source images you have permission to edit.
  • Respect consent and rights when depicting real people.
  • Provider safety rules apply to prompts and reference images.