PROMPT LIBRARY
Seedream 5.5 prompts, each with the image it made.
Each prompt is quoted word for word from the model maker's guide or a creator's post, next to the output it produced. Open a card for the full prompt.
ByteDance Seed released Seedream 5.5 on November 9, 2026, as its next image creation model. It brings three upgrades: multi-turn editing that keeps unedited regions identical at the pixel level for up to 100 rounds, native RGBA output with full and partial transparency, and more lifelike light and skin with clearer small text. A Pro version is announced to follow. The prompts below open with ones creators shared on X, each linked to its post, followed by ByteDance's own examples from the Seedream 5.5 page. Every prompt is quoted word for word with the image it made.
Sources: ByteDance Seed: Seedream 5.5 · Introducing Seedream 5.5
Try Seedream 5.5 on Higgsfield
This is an affiliate link: AgentCraft earns a commission when you subscribe through it, and your price stays the same.
Seedream 5.5 prompts: how ByteDance writes its own examples →
Seedance 2.5 prompts, ByteDance's video model →
Updated 2026-11-11 · 20 prompts, newest first
Other model pages: GPT Image 2.6 · Nano Banana 2.1 · Seedance 2.5 · Kling 4.0 · MiniMax H3 · Wan 3.0
Woman with dried flowers beside a Soviet bus
Quilled paper woman dancing with rainbow umbrella
Rooftop chess player in green faux fur coat
Woman glancing back on subway escalator, 35mm look
BERRY CLUB blueberry character board in two languages
Blue morpho butterfly infographic in Chinese and English
Bear, red panda and otter build a glider above the clouds
Donkey peering through a fence gap, ultra wide close-up
Two older diners in a European bistro on a summer evening
Father holding a sleeping baby on a sofa in window light
FROM SEED TO SALAD six stage garden infographic
Lemon wall, purple door and linen in hard afternoon sun
PRINT PLAY graffiti collage poster
Golden building reflected in puddles after rain
Shakespeare literary newspaper with seven short articles
Commuters streaming along a subway platform
Water droplets lifted from a tiny pool spell seedream
White cat among bar bottles in flash film light
Windswept woman on her phone in a tilted street frame
Nothing matches. Try a shorter word.
Seedream 5.5 prompts worth starting from
The most liked prompt in each category on this page, in full, with what makes it work. Copy one, then change the subject.
Slytherin girl smiling in candlelit Hogwarts library
A reference image locks the character design, and the prompt then lists the uniform and colours item by item so the outfit stays exact. Light comes from two sources, a warm candle on the left and cool blue twilight through the window, which gives the scene depth.
Use @ image as the exact character design: long pale-blonde hair, grey eyes, Slytherin uniform with grey sweater vest, green-and-silver striped tie and black robe with green lining. High-quality anime illustration, upper-body shot of her sitting at a long wooden table in the Hogwarts library at dusk, turning her head toward the viewer with a sly, confident smile. Her hands are out of frame. Warm candlelight from the left lights her face and hair, cool blue twilight comes through the tall arched window behind her, glowing dust in the air, stacks of old books softly blurred in the background. Clean line art, rich soft lighting, detailed hair strands, no text. Woman with dried flowers beside a Soviet bus
The prompt builds the scene in a fixed order: a named vehicle and setting, then a clothing list, then framing rules (knees up, off center, eye level) and a lighting setup. The 50mm lens, film grain and a negative prompt keep the result close to candid film street photography rather than a glossy modern shoot.
Photorealistic fashion editorial with the atmosphere of a winter morning in the early 1990s, in a Soviet-era residential neighborhood. A beautiful adult brunette woman with delicate facial features stands beside the open folding doors of an aged cream-and-red Soviet LiAZ-677 city bus. She holds a small bouquet of dried wildflowers wrapped in vintage brown kraft paper, gently gripping it with both hands in front of her thighs.
She wears an oversized charcoal wool coat, a soft ivory knitted scarf, a dark burgundy ribbed sweater, straight dark trousers and black leather winter boots. Loose dark brown hair falls naturally around her face, a few strands lifted by the freezing wind. Flushed cheeks, minimal makeup, thoughtful expression, looking slightly past the camera, shoulders gently raised against the cold.
Snow-covered pavement, compacted gray snow beside the bus wheels, frosted windows with condensation, faded red paint, weathered metal. Blurred Soviet apartment blocks and a modest bus shelter in the distance. Fine snowflakes in the air, visible breath. The delicate dried flowers add a subtle warm color accent against the muted winter surroundings.
Three-quarter portrait framed from the knees up, eye-level camera, woman placed off-center, the bus filling one side of the composition. Cold overcast daylight with direct on-camera flash, crisp face, deep background, subtle analog film grain, restrained colors, candid 1990s street photography combined with luxury fashion editorial. Real skin texture, tactile wool, believable hands and bouquet construction, shot on a 50mm lens --ar 3:4 --style raw --s 150 --no modern cars smartphones logos text watermark Quilled paper woman dancing with rainbow umbrella
Naming the medium as coiled paper strips and quilled butterflies, plus a matte charcoal cardstock backdrop with overhead studio light, makes the output read as a real paper sculpture. The ordered colour list for the gradient keeps the rainbow transitions consistent across the dress, umbrella and water ripples.
3D paper quilling art of a graceful woman dancing in side-profile. She wears an elegant sleeveless v-neck dress made of intricately coiled paper strips in a vivid rainbow gradient—transitioning seamlessly through yellow, orange, red, magenta, deep purple, royal blue, and emerald green.
Her long brown hair flows in the wind behind her as she gracefully holds an open quilled umbrella featuring matching rainbow paper panels overhead. She wears bright red high heels, standing atop quilled paper water ripples reflecting vibrant hues. Surrounding her in mid-air are multiple detailed quilled paper butterflies in shades of bright orange, yellow, pink, and sky blue.
The background is a solid matte dark charcoal grey cardstock, featuring subtle overhead studio directional lighting that casts soft 3D drop shadows underneath the layered paper elements, emphasizing realistic texture and depth. High detail, paper craft sculpture aesthetic, 4k resolution. --ar 2:3 Rooftop chess player in green faux fur coat
The prompt fixes the camera at chessboard height with a 20mm wide angle lens, so the foreground king looms large while the board recedes. It also names the camera body and exposure to lock in a photographic look, and the no smoothing and no CGI clauses keep skin and fabric texture real.
I tested all four models directly in
@magnific
Prompt: An ultra-realistic high-fashion editorial photograph of a striking 28-year-old Japanese man with sharp facial features, a defined jawline, slightly messy medium-length black hair and narrow rectangular black sunglasses, sitting confidently on a rooftop terrace while playing chess.
He wears an oversized luxurious emerald-green faux-fur coat over a black silk shirt, tailored black trousers and a subtle silver chain necklace. His expression is calm, confident and slightly intimidating, looking directly toward the camera.
Camera composition: An extreme low-angle shot taken from the very edge of a chessboard, with the camera positioned only a few centimeters above the board's surface. The black-and-white chessboard dominates the entire bottom third of the frame, its squares appearing exceptionally large in the foreground and rapidly shrinking toward the seated man.
The man is centered in the composition, visible from approximately the knees upward, leaning slightly forward. His right arm extends directly toward the camera, with his hand dramatically enlarged by perspective. He is gripping the top of a polished ivory wooden king chess piece between his thumb and index finger, moving it toward an empty square near the camera. The king is dramatically oversized in the immediate foreground due to the wide-angle perspective, while the remaining chess pieces appear progressively smaller toward the background.
His other hand rests naturally near his knee. The chess pieces are physically accurate and positioned naturally on the board, with realistic contact shadows and detailed polished wooden surfaces.
Environment: An open urban rooftop with subtle concrete architectural details, low surrounding rooftops and an enormous vivid cyan-blue sky with a few soft, scattered white clouds. The bright sky occupies the upper half of the composition, creating strong visual contrast against the emerald-green coat.
Photography: Shot on a Sony A1 II with a 20mm wide-angle lens, camera placed at chessboard level, f/8, ISO 100, 1/1000s. Deep environmental perspective, exaggerated foreground scale, realistic optical distortion, crisp textures across the chessboard and subject. Bright natural midday sunlight, accurate skin tones, natural facial asymmetry, individual hair strands, detailed fabric and fur fibers, subtle imperfections and physically realistic shadows.
Authentic luxury fashion campaign photography, bold editorial framing, natural photographic color grading, exceptionally realistic skin texture, no artificial skin smoothing, no CGI appearance, no illustration, no plastic textures, no excessive cinematic effects. Prompts for the same jobs, tested on other models
Each prompt names in brackets the model its image came from. Run it on Seedream 5.5 and compare.
Shampoo bottle cut out on transparent background (tested on GPT Image 2.6)
Explicit output constraints keep the cutout clean: a centered product, no halos, label text preserved exactly, and no backdrop or shadow. Forbidding any restyling keeps the product faithful to the input photo.
Extract the product from the input image and isolate it on a fully transparent background.
Output: centered product, crisp silhouette, no halos/fringing.
Preserve product geometry and label legibility exactly.
Add only light polishing. Do not add a solid backdrop, checkerboard, scenery, or shadow.
Do not restyle the product; remove the background and preserve clean alpha transparency. Bakery logo on a transparent background (tested on GPT Image 2.5)
Asks for an original flat mark that reads at small and large sizes, then spells out the transparent background with clean alpha edges and no backdrop, checkerboard or watermark. Pair it with background=transparent in the API.
Create an original, non-infringing logo for a company called Field & Flour, a local bakery.
The logo should feel warm, simple, and timeless. Use clean, vector-like shapes, a strong silhouette, and balanced negative space.
Favor simplicity over detail so it reads clearly at small and large sizes. Flat design, minimal strokes, no gradients unless essential.
Fully transparent background. Deliver a single centered logo with generous padding, clean alpha edges, and no solid backdrop, scenery, checkerboard, or watermark. Kawaii Cactus Die-Cut Sticker (tested on GPT Image 2)
Exact counts for arms, eyes, cheeks and petals keep the character anatomy stable. Style cues such as thick outlines, a white die-cut border and a transparent background make the result print-ready.
Create a cute printable sticker illustration on a transparent background: a kawaii green cactus in a terracotta flower pot, centered and filling most of a square canvas. The cactus has one large oval ribbed central body and exactly 2 curved side arms, one on the left and one on the right, both raised upward. Give it a happy face with exactly 2 glossy black oval eyes, 2 pink circular blush cheeks, and 1 open smiling mouth with a dark interior and pink tongue. Add a red-pink flower on top-left of the cactus with exactly 6 rounded petals and a cluster of small yellow dots in the center. Cover the cactus with many small star-shaped cream spines with orange bases, distributed across the main body and both arms. Place the cactus in an orange terracotta pot with a thick rim, darker orange shading, small speckles, and glossy highlights; show brown soil and several rounded pebbles at the top. Use a polished digital cartoon style with thick dark green outlines, soft gradients, shiny highlights, saturated colors, and a clean die-cut sticker look with a thick white border around the entire cactus and pot. Background should be transparent, optionally previewed by a light gray checkerboard only to indicate transparency. No text, no watermark, no extra objects. Encyclopedia infographic card of the James Webb Telescope (tested on GPT Image 2)
A TOPIC placeholder is filled in by a list of modular panel types such as profile, taxonomy, pros and cons, and rating summary. Explicit style anchors like collectible handbook and natural history guidebook, plus a light background and rounded boxes, keep the layout consistent across a series.
Create educational encyclopedia style images with GPT Image 2 on
@itsPolloAI
Prompt: Based on { TOPIC }, create a high-quality vertical “encyclopedia-style educational infographic image.”
This image should NOT look like a regular poster or a simple illustration. Instead, it should feel like a structured knowledge guide that combines:
the feeling of a collectible reference handbook
a modern encyclopedia page
a lifestyle knowledge card
and a highly shareable social-media infographic
The overall style should resemble a premium natural-history guidebook mixed with modern editorial infographic design.
The image should include:
One beautiful and highly detailed main subject image
Several zoomed-in detail sections highlighting important features
Multiple modular information panels with rounded corners
Clear title hierarchy and highlighted key labels
Concise yet information-rich encyclopedia content
Visual scoring systems, quick summaries, or “Top 5” modules
The information sections should automatically adapt to the topic. Select and combine relevant categories such as:
Basic profile
Classification / taxonomy
Physical characteristics
Behavior / ecology / habits
Structure or formation mechanisms
Growth conditions or usage methods
Care, maintenance, or optimization tips
Risks, warnings, and important notes
Suitable users or application scenarios
Pros and cons comparison
Quick rating tags or summary cards
Visual requirements:
Clean light-colored background
Soft and elegant color palette
Gentle shadows
Small refined icons
Rounded information boxes
Organized editorial layout
High information density without feeling crowded
Comfortable reading experience
The final result should feel like a real publishable encyclopedia knowledge card designed for reading, collecting, and creating as part of a consistent series — NOT like a commercial advertisement poster.
The image must strongly emphasize:
“knowledge integration + modular information design + handbook/reference-style presentation.” Endangered Bengal Tiger Annotated Infographic Poster (tested on GPT Image 2)
The prompt asks for a photorealistic central animal supported by annotated callouts, icons and color blocking, instead of generic sections. Having the model research a real species first fills the layered layout with accurate, dense facts.
Animal Infographic by GPT Image 2 on ChatGPT app
Prompt: Create a visually rich infographic about an endangered animal. Start by finding one online, research its habitat, diet, and unique traits. Present information through annotated visuals and structured callouts, not generic sections. Style it like a bold graphic illustration: a detailed, photorealistic central animal as the focal point, supported by diagrams, callouts, and concise text elements. Use clean backgrounds and a mix of photorealism with strong graphic elements (shapes, icons, color blocking) in a layered composition. Make it dense, tactile, and professionally authored. Blurred Flash Snapshot on Night Tokyo Sidewalk (tested on GPT Image 2)
Stacks accidental phone camera cues such as flash during motion, handheld shake, directional blur, blown highlights and heavy noise to fake a raw snapshot. The negative prompt blocks studio lighting, sharp focus and identity matching.
GPT Image 2
{
"prompt": "Ultra-realistic candid smartphone photo, 3:4 vertical. Original non-identifiable young woman inspired only by general proportions/vibe. Night Tokyo sidewalk beside white ceramic tile wall. Mid-walk, half-profile, turning back in surprise, hand raised toward lens, shy restrained smile, continuing forward, imperfect framing, nearly exiting frame. Flash fired during motion. Strong handheld shake, heavy directional blur, smeared facial details, blurred hand and hair, ghosting, streaked tile wall, deep darkness around. Harsh flash highlights, blown exposure, hard shadows. Raw accidental snapshot, intrusive, playful, fleeting memory. Extremely noisy, heavily blurred, authentic phone-camera look.",
"negative_prompt": "identity match, face copy, real person replication, anime, illustration, painting, stylized, studio lighting, beauty lighting, sharp focus, clean face, smooth skin, posed portrait, fashion editorial, cinematic, film still, tripod, professional photography"
} Man in Adidas windbreaker covering mouth by shutter (tested on ChatGPT / Gemini)
The prompt pins the garment details (stripes on both sleeves, chest trefoil logo, drawstring hood), the pose (hand covering nose and mouth, lower hand with motion blur) and the background, so each one appears in the output. Harsh direct flash against a dark ribbed shutter gives the high contrast street look.
A raw, street-style, candid photograph of a young Asian man standing in a medium waist-up shot. He is wearing a white oversized Adidas original windbreaker jacket with iconic black three-stripes down both sleeves and a small trefoil logo on the chest, a high neck with a hoodie and drawstrings, and black pants. His dark, naturally messy and voluminous hair frames his face. He is looking down and away from the camera, bringing his right hand up to cover his lower face (nose and mouth) in a cool, pensive gesture. His left hand, held lower, shows noticeable motion blur, adding realism. The background is a weathered, dark blue-black metal security shutter door with repetitive horizontal ribs, creating an industrial, urban environment. The lighting is harsh direct flash, brightly illuminating the man and casting deep shadows on his face and sharp shadows onto the shutter behind him, making him stand out. The color palette is high-contrast black, white, and deep urban blues/grays. The texture is gritty with film grain. Composition is eye-level, slightly off-center to the left. 35mm photograph, high contrast, moody atmosphere, cinematic urban street photography, 4k, photorealistic, cinematic lighting Olive-suited man with natural skin texture (tested on Nano Banana 2.1)
Two texture reference images are passed alongside the character sheet, and the prompt locks identity, pose, clothing and layout while changing only skin micro texture and hair strand structure. An explicit contrast rule softens blotchy faces without retouching, and the prompt is written for Seedream 5.0 Flash.
How it works:
→ Image 1 — character sheet
→ Image 2 — skin texture
→ Image 3 — hair texture (light or dark)
Universal prompt for Seedream 5.0 Flash (works across characters): Keep <<<image_1>>> exactly as it is: same person, same face shape and features, same expression, same hairstyle and hair shape, same hair color, same skin tone, same makeup, same wrinkles, freckles, moles, scars and facial hair, same clothing and accessories, same pose, composition, layout, background and framing.
Change only the surface texture:
- Skin: apply the micro-texture from <<<image_2>>> — fine natural skin lines, pores and soft realistic surface. Do not copy its color or its glossy shine.
- Hair: apply the strand structure from <<<image_3>>> — fine individual strands, soft natural flyaways. Do not copy its color.
Balance the contrast to a natural photographic level: if image 1 looks too harsh or blotchy, soften it; if it looks flat or washed out, add depth. Aim for a well-balanced realistic photo — rich but not crushed shadows, clean highlights, smooth even tonal transitions, natural shading with real volume. No retouching, no beautifying, no plastic look. How to write prompts for this model
Write it like a short photo brief
ByteDance's 15 examples are short: a median of 417 characters, about 63 words in four sentences. 9 of them call the image a photograph or a snapshot, 13 name a texture, grain or fine detail, and 8 describe the light. Compare the 1,749 character median of the creator prompts on our Nano Banana 2.1 page: for Seedream 5.5, a few concrete choices go a long way. Source: ByteDance Seed: Seedream 5.5
Give the exact words, then the type and layout
6 of the 15 examples quote the exact text to render, such as a masthead, a headline or a Chinese tagline, then add the type style and where it sits. ByteDance reports a severe text corruption rate of 0.4% and a minor rate of 1.7% in its own Chinese and English tests, so dense small type is worth asking for. Source: Introducing Seedream 5.5
Set the orientation and count the parts
9 of the examples open with vertical, horizontal, landscape or a ratio such as 3:4. Layouts list their parts with numbers: the character board asks for four variants, five expressions and six accessories, and the garden infographic names six stages joined by five arrows. Source: ByteDance Seed: Seedream 5.5
Ask for transparency in the prompt
Seedream 5.5 outputs RGBA images directly. ByteDance's transparent examples say it in words: each character as a separate image with a transparent background, or keep the area outside each circle transparent. Say which parts stay opaque and which stay clear. Source: ByteDance Seed: Seedream 5.5
Edit in rounds, one change at a time
In ByteDance's demo, 100 successive edits used each round's output as the next input, changing clothing, accessories and props while the rest stayed fixed. Name the one object to change in each turn, and the model keeps the unedited regions at the pixel level. Source: Introducing Seedream 5.5
Where to try Seedream 5.5
In China, use Jimeng (即梦). Elsewhere, Dreamina by CapCut offers it in the browser, and developers can call it through BytePlus ModelArk or try it in the BytePlus playground. Higgsfield also lists Seedream 5.5; our link to it, at the top of this page, is an affiliate link. Source: Jimeng · Dreamina · BytePlus playground · BytePlus Seedream
Questions about this model
What is Seedream 5.5?
ByteDance Seed's image creation model, released on November 9, 2026. It generates and edits images, with three upgrades over the previous version: stable multi-turn editing, native transparent RGBA output, and more realistic images with clearer text. Source: Introducing Seedream 5.5
What is new compared with Seedream 5.0?
In ByteDance's tests across six production use cases, Seedream 5.5 scored higher than Seedream 5.0 Pro in every one, and its usability rate more than doubled in film and television and in office work. In paired comparisons it reached +55.62% for realism in image-to-image tasks. Source: Introducing Seedream 5.5
Can Seedream 5.5 make images with a transparent background?
Yes. It generates RGBA images with an alpha channel, with full and partial transparency, so stickers, characters and lettering come out ready to place on any layout. Source: Introducing Seedream 5.5
How many times can I edit the same image?
ByteDance shows 100 successive edits on one portrait, each using the previous output, with small objects such as rings and glasses frames still edited precisely at the end. Source: Introducing Seedream 5.5
How does Seedream 5.5 compare with GPT Image 2.5 and Nano Banana 2.1?
In ByteDance's own expert evaluation, Seedream 5.5 leads GPT Image 2.5 Sunburst and Nano Banana 2.1 in text structure for both text-to-image and image-to-image, and shows a clear advantage in text-to-image realism. These are the maker's own results; our GPT Image 2.6 and Nano Banana 2.1 pages let you compare prompts side by side. Source: Introducing Seedream 5.5
Is there a Seedream 5.5 Pro?
ByteDance says a Pro version of the Seedream 5.5 series will follow. Source: Introducing Seedream 5.5
How long should a Seedream 5.5 prompt be?
ByteDance's own examples run from 183 to 536 characters, a median of 417. The shortest, water droplets that spell a word, works because one clear idea carries the image. Source: ByteDance Seed: Seedream 5.5