Seedream 4.5 AI Image Generator
Seedream 4.5 is ByteDance's photoreal text-to-image model, sitting between Seedream 4.0 and the 5.0 line. It takes a prompt, an aspect ratio and a quality setting, and returns a single image.
Seedream 4.5 AI Image Generator
From prompt to image
Four steps, and the third is the one that changes the result most.
Pick the ratio first
Decide the shape before you write, because framing changes what belongs in the prompt.
Describe the light
Photoreal models respond to stated lighting far more than to adjectives like beautiful or stunning.
Quote any text exactly
Put the words you want rendered in the prompt verbatim. Paraphrasing them is how they come back wrong.
Run it twice
Two images at 25 credits each is a cheaper way to find the shot than rewriting the prompt blind.
What is Seedream 4.5?
Seedream 4.5 is a text-to-image model in ByteDance's Seedream family, positioned above 4.0 and below the 5.0 Lite and 5.0 Pro tiers. It takes three things: a written prompt, one of eight aspect ratios, and a quality setting of basic or high. There is no separate resolution ladder and no image count — one request returns one image.
What it is good at is the photoreal end of the range: material surfaces, skin, and the small print inside a scene. Text rendering is the part most worth knowing about, because it is where image models have historically failed in a way that is obvious to anyone looking; asking 4.5 for a sign, a label or a book spine returns something readable far more often than the generation before it did.
It is not an editor. Handing it an existing image to modify is a different model id on both shelves, and that path is not wired here.
Creative engine
What an image costs
One flat rate per generated image, independent of the aspect ratio you choose.
Between 4.0 and the 5.0 line
The mid tier of the Seedream family, tuned for photoreal detail and readable in-scene text.
Three inputs, no more
Prompt, aspect ratio, quality. There is no seed, no batch and no resolution field.
Text to image only
Editing an existing image is a separate model and is not available on this page.
When 4.5 is the right pick
Pick 4.5 when the image has to look photographed and has to contain writing. That combination is narrower than it sounds and it is exactly where the cheaper tiers give up: Seedream 4.0 will produce a handsome image and turn the sign in the background into ornamental squiggles. Go up to 5.0 Pro when the subject is a person in motion, or when you need the extra fidelity of its high quality setting. Stay on 4.0 when the picture is decorative and nobody will read anything inside it. The prompt transfers between all three, so testing down the ladder costs almost nothing. When the writing is the whole picture rather than a sign inside it — a headline, a set of numbered steps, a caption under every panel — [Qwen Image 3](/image/qwen-image-3) is built for that specific job.
Signs, labels and packaging
Anything where the words in the frame are part of the point rather than set dressing.
Material and surface
Rust, condensation, worn leather, wet rope — texture is where photoreal is won or lost.
Fixed ratio from the start
Generating at 21:9 or 9:16 directly beats cropping a square down to it afterwards.
Feature overview
What the model accepts, and what it deliberately does not.
Text to image
One prompt in, one image out, with no source material required.
Eight aspect ratios
1:1, 4:3, 3:4, 16:9, 9:16, 2:3, 3:2 and 21:9.
Basic and high quality
Two settings rather than a resolution ladder; basic is what this page generates by default.
In-scene typography
Words asked for inside the image come back legible more reliably than on 4.0.
Seedream 4.5 specs
Taken from the model's published API schema.
- Model
- Seedream 4.5 (ByteDance), text-to-image
- Required inputs
- Prompt, aspect ratio, quality
- Aspect ratios
- 1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 2:3 / 3:2 / 21:9
- Quality
- basic or high
- Images per request
- One
- Credit cost
- About 25 credits per image
- Image editing
- A separate model id on the provider; not offered on this page
What people generate with it
Jobs where the image has to survive being looked at closely.
Product and packaging shots
Labels, bottles and boxes where the printed text has to read correctly.
Editorial photography
People and places lit like a magazine shoot rather than an illustration.
Storefronts and signage
Scenes built around lettering — shop fronts, menus, street signs.
Flat lays and still life
Overhead arrangements where every object has to hold its own detail.
SayMaker pricing — you pay per generation, never per seat
One credit pool covers Nano Banana images and Seedance and Veo video. The cost shows before every run, the safety check runs before the model does, and a failed run is refunded automatically. Use a subscription for ongoing work, or a one-time pack when you just need to top up.
Free
What's included
- 15 credits before you sign up
- +40 when you create an account
- +100 a week from daily check-ins
- = 488 a month — 97 images or 12 videos
- No card, no account
- Free engine every day Grok Imagine
- Photo editing Nano Banana 2 Lite
- Not included: Clean downloads, no watermark
- Not included: Every model unlocked
- Not included: No shared queue
Secure checkout by Stripe. Card details never touch our servers.
Starter
What's included
- 3,150 credits per month
- Up to 630 images or 78 videos Grok Imagine Nano Banana
- Clean downloads, no watermark
- Every model unlocked Veo 3.1 Seedance Nano Banana
- Cost shown before you generate
- Generation history
Secure checkout by Stripe. Card details never touch our servers.
Creator
What's included
- 7,200 credits per month
- Up to 1,440 images or 180 videos Grok Imagine Nano Banana
- Clean downloads, no watermark
- Every model unlocked Veo 3.1 Seedance 2 Nano Banana 2
- No shared queue
- Priority credit top-ups
Secure checkout by Stripe. Card details never touch our servers.
Studio
What's included
- 13,200 credits per month
- Up to 2,640 images or 330 videos Grok Imagine Nano Banana
- Clean downloads, no watermark
- Every model unlocked Seedance 2.5 Kling 3.0 Veo 3.1
- No shared queue
- Built for 4K runs
Secure checkout by Stripe. Card details never touch our servers.
Credit packs
One-time top-ups — buy extra credits any time you run low.
Credit Pack 1500
What's included
- 1,500 credits that never expire
- Up to 300 images or 37 videos Grok Imagine Nano Banana
- Clean downloads, no watermark
- No ongoing subscription
- Available across the supported models
- Credits never expire
Secure checkout by Stripe. Card details never touch our servers.
Credit Pack 3600
What's included
- 3,600 credits that never expire
- Up to 720 images or 90 videos Grok Imagine Nano Banana
- Clean downloads, no watermark
- No ongoing subscription
- Available across the supported models
- Use for both video and image generation
- Credits never expire
Secure checkout by Stripe. Card details never touch our servers.
Credit Pack 9000
What's included
- 9,000 credits that never expire
- Up to 1,800 images or 225 videos Grok Imagine Nano Banana
- Clean downloads, no watermark
- No ongoing subscription
- Handy for Seedance 2.0 final renders
- Credits never expire
Secure checkout by Stripe. Card details never touch our servers.
Charges appear as “SAYMAKER AI” on your card statement. You can cancel any time from Settings → Billing; cancellation takes effect at the end of the period you already paid for. Operator details, the full model list, and the refund window are on the about page.
Powered by
One credit balance for every SayMaker image and video model
Use one balance across every image and video model on the shelf — the main ones are listed below — and check the credit cost before each request.
Video models
Image models
Model credit guide
What each model costs in credits
A failed run is refunded automatically. The exact estimate in the generator varies by model, length, resolution, audio, and number of images.
| Type | Model | Credit cost |
|---|---|---|
| Video | Seedance 2.5 | The long-take tier, priced per second: 5s 480p ≈ 525 credits, 5s 720p ≈ 1,185. A full 30s take runs ≈ 3,150 at 480p and ≈ 7,090 at 720p. |
| Video | Seedance 2.0 | Supplying a starting frame or clip costs less than starting from words alone: 6s 720p ≈ 565 credits from an image, ≈ 925 from text. Scales with resolution and length. |
| Video | Seedance 2 Fast | Faster and lower cost. 6s 720p text-to-video ≈ 745 credits. |
| Video | Seedance 2 Mini | The cheapest tier of the Seedance 2 family. 6s 720p ≈ 465 credits, 6s 480p ≈ 215 credits. |
| Video | Seedance 1.5 Pro | Audio doubles the rate. 6s 720p ≈ 85 credits silent, ≈ 160 with audio; 1080p ≈ 175 and ≈ 340. |
| Video | Veo 3.1 | Billed per video, not per second, and the tier you pick is the whole price: Lite ≈ 115 credits at 720p and ≈ 135 at 1080p, Fast ≈ 225 at 720p, Quality ≈ 940 at 720p. |
| Video | Kling 3.0 | Audio raises the rate by about half. 6s 720p ≈ 320 credits silent, ≈ 455 with audio; 1080p ≈ 405 and ≈ 610. |
| Video | MiniMax H3 | Fixed 2K, no resolution ladder. Priced per second — a 5s clip ≈ 395 credits. |
| Image | Nano Banana 2 | Generate or edit from text and images. 20 credits per 1K image, 30 at 2K, 45 at 4K. |
| Image | Nano Banana Pro | Consistent run times across generations. 30 credits per 1K or 2K image, 55 at 4K. |
| Image | Nano Banana 2 Lite | Faster, simpler variant, and the everyday editing price: a flat 15 credits per image at every resolution. |
| Image | GPT Image 2 | The lowest-cost premium image model here. 10 credits per 1K image, 15 at 2K, 30 at 4K. |
| Image | GPT Image 2.5 Flare | OpenAI's newest image model, on the fast tier. 25 credits per 1K image, 40 at 2K, 60 at 4K — same price whether you generate or edit. |
| Image | GPT Image 2.5 Sunburst | The 2.5 tier for edits that touch only what you named. Same price as Flare: 25 credits per 1K image, 40 at 2K, 60 at 4K. |
| Image | Seedream 5.0 Lite | Flat pricing — 20 credits per image whether you generate or edit. |
Seedream 4.5 FAQ
Common questions about the mid tier of the Seedream family.
4.5 is the newer generation and is noticeably better at rendering text inside an image. 4.0 takes an image size and a 1K/2K/4K resolution instead of a quality setting, and costs a little less.
About 25 credits, flat, whichever aspect ratio you choose. Seedream 4.0 is about 20 and Seedream 5.0 Pro about 30 at its basic setting.
Not on this page. Seedream editing is a separate model id on the provider, and only the text-to-image path is wired here.
They are the two settings the API exposes. This page generates at basic; on the 5.0 Pro tier the same switch is also a price difference, which is why it is sent explicitly rather than left to a default.
Often, and far more often than earlier models, but not guaranteed. Quote the text verbatim and keep it short — long paragraphs inside an image are still unreliable on every model.
Credits are returned automatically, unless the request broke the content policy.
4.5 is the middle child on purpose: flat 25 credits, more detail than 4.0, more predictable than the 5.0 line. It is the safe default for batch work where you want one engine's consistent look across fifty images.
Make an image with Seedream 4.5
Pick a ratio, write the scene, quote any text you want in it, and run it.