@LinusEkenstam: Here is how to generate that first poster: Reference Image + Prompt Full Prompt: Create a vertical streetwear editorial…
Summary
Seedream 5.0 Pro is a highly controllable AI image generation and editing model that works with reference images and prompts. It is available via BytePlus API and can be used directly on Lumina for tasks like making ads, editing characters, and creating blueprints.
View Cached Full Text
Cached at: 07/12/26, 07:01 PM
Seedream 5.0 Pro allows for hyper controllable edits.
- Use Seedream 5.0 Pro (2k)
- Upload a reference photo
- Paste prompt (in alt + below)
Works well for humans, items, and animals
Enterprises and Developers can access the official API via @BytePlusGlobal, and you can also use it directly on BytePlus @lumina_ai_aiart
Watch me make ads, edit a character, and create blueprints.
Let’s look at some more examples on how you can direct using Seedream 5.0 PRO inside Lumina below in the thread
Here is how to generate that first poster:
Reference Image + Prompt
Full Prompt:
Create a vertical streetwear editorial poster with a bold youth-culture aesthetic. Use an off-white paper background and a clean magazine-style layout.
At the top, place oversized rounded bubble typography reading “CITY JUMP” in deep cobalt blue. The letters are thick, soft, playful, tightly spaced, and partially hidden behind the central photo.
In the center, place a large vertical action photograph of a young European man performing an energetic skateboard-style jump toward the camera in a modern urban plaza. He wears a orange open shirt, a shirt, black baggy pants, white crew socks, and black and white Nike Air sneakers.
Use an extreme low-angle fisheye lens from ground level. His front shoe is dramatically enlarged and dominates the foreground, while his face and upper body appear smaller in the background. One arm stretches sideways for balance, while the other hand tightly holds the wide black strap of a large black messenger bag positioned close to the right side of the camera. The bag’s rectangular silver buckle should be clearly visible and sharply detailed.
Bright blue sky with soft white clouds, modern glass-and-steel architecture, outdoor stairs, tiled pavement, strong midday sunlight, realistic shadows. Add subtle radial motion blur around the edges and background to emphasize fast movement, while keeping the person, shoe, bag strap, and buckle sharp.
Add a rough hand-drawn red oval annotation around the silver buckle on the black bag, as if marked with a red grease pencil.
At the bottom of the poster, include small cobalt-blue editorial text:
Left side: “seedream 5.0” “move pro”
Right side: “stay hungry” “carry fuel”
Add a decorative cobalt-blue barcode graphic beneath the left text.
Style: contemporary streetwear campaign, skateboarding photography, Gen-Z fashion editorial, experimental sports advertising, bold typography, dynamic forced perspective, vibrant blue and green color palette
But you can also generate character sheets, and work as a art director and just scribble your edits on top.
Here is my prompt for this:
-
My Reference selfie photo
-
The full (editable) prompt:
-
“A full-body studio portrait of a man standing in a bold, wide-legged confident stance, feet planted firmly apart, one hand casually tucked near his waistband, facing the camera directly. He has long, open brown hair flowing loosely to shoulder length, slightly tousled. He wears a crimson red linen shirt with a rugged, textured weave and visible natural creases, sleeves folded up to the forearms, the front left casually unbuttoned to reveal a fitted black t-shirt underneath. He pairs this with relaxed-fit black pants with a slightly loose, dropped silhouette. On his feet, he wears black-and-white leather sneakers that complement the dark tones of the outfit. The lighting is soft, even studio lighting against a clean off-white background, casting a subtle natural shadow beneath him. The image has a realistic, editorial fashion-photography quality with sharp focus on texture.. the linen grain of the shirt, the knit of the t-shirt, and the folds of the pants all clearly rendered. Camera angle is slightly low, shooting straight-on, full body in frame, similar to a streetwear lookbook photo.”
You can make simple singular edits, BUT I got very surprised about what happened when I threw more edits at it.
Here I put all the edits in one photo and passed it through with the simple prompt: “follow instructions in the image”.
Honestly, you’ll find me like this a few years from now down in South of France, just having a good time. Especially need them golden Air Force Ones.
But it does not end there, you can use your annotation art direction to take your character in any direction that you want. So why don’t we try the Pirate route, because I get pirate vibes.
We can see there is some slight drift in the pose, but to be fair, I was not explicit.
But it does not stop there, the Seedream model can also do highly detailed images with loads of information in them. So let’s turn our pirate into a model kit with detail descriptions.
You can also create full character sheets with single reference image and prompt. This is very useful if you want to feed references in to Seedance when creating videos and you need character consistency.
It can also do text rendering and very detailed outputs when combining images together.
Get access here today:
Enjoyed this?
Follow @linusekenstam for more AI news & tutorials!
Please like, repost, and bookmark the main tweet; it really supports me to keep making this kind of content.
Similar Articles
@LinusEkenstam: Seedream 5.0 Pro allows for hyper controllable edits. 1. Use Seedream 5.0 Pro (2k) 2. Upload a reference photo 3. Paste…
Seedream 5.0 Pro is a highly controllable AI image editing model, accessible via BytePlusGlobal API and Lumina platform, enabling precise edits for humans, items, and animals.
BREAKING: ByteDance have announced Seedream 5.0 Pro
ByteDance launches Seedream 5.0 Pro, a multimodal image creation model with breakthroughs in complex information visualization, interactive precision editing, realistic imagery, and native multilingual support.
ByteDance debuts Seedream 5.0 Pro with advanced reasoning (2 minute read)
ByteDance debuts Seedream 5.0 Pro, a multimodal image-creation model for production design with advanced reasoning, complex visualization, precise editing, realistic textures, and native multilingual support.
@DeRonin_: this is how the best teams are solving creative production in 2026 the gap: - anyone can generate one AI image or video…
Melius is a creative production platform that uses AI agents to generate consistent brand assets across multiple models like GPT Image 2, Seedance, Kling, and HeyGen, allowing teams to create hundreds of campaign variants quickly.
@VraserX: This looks like a pretty big step for AI design. What stands out to me is that this is not just about generating pretty…
Genspark launches Genspark Design, an AI design tool powered by Claude Opus 4.7 that can create UI prototypes, posters, videos, HTML animations, and convert designs into code, aiming to be a full creative production tool.