Image with text Runs on our GPU
Bold titles, clean graphics. Thumbnails, posters and flat illustrations with short English titles.
1 credit · under a minute on our GPU with Thumbnail · 1280x720
Z-Image-Turbo draws a picture and can write a short English title into it, which most image models cannot. It also makes clean flat or isometric illustrations. Check the spelling before you publish.
What you can do
Each example is a real run on our GPU: what went in, the exact instruction, and the result exactly as the model made it. Pick one to see it, then start from the same instruction.
Only the instruction: no file.
What we asked
YouTube thumbnail, bold large title text "FREE PDF TOOLS" in white with a yellow outline, dark blue gradient background, a glowing PDF document icon and a laptop, high contrast, no people
What came out, untouched
36 s on our RTX 4060 1 credit ($0.10) · Thumbnail · 1280x720
Only the instruction: no file.
What we asked
flat vector illustration, isometric style, a friendly toolbox with floating document, camera and microphone icons, soft pastel palette, clean shapes, white background, no text, no people
What came out, untouched
42 s on our RTX 4060 2 credits ($0.20) · Square · 1024x1024
2 examples from our own runs, with the times we measured. Open "Prompt and settings we used" under any of them for the exact input.
YouTube thumbnail with a title
Sharp and bold, but it wrote 'PDD' instead of 'PDF': always check spelling.
Prompt
YouTube thumbnail, bold large title text "FREE PDF TOOLS" in white with a yellow outline, dark blue gradient background, a glowing PDF document icon and a laptop, high contrast, no people
Flat isometric illustration
Clean vector look, no photo texture. Also the input of the 3D toolbox example.
Prompt
flat vector illustration, isometric style, a friendly toolbox with floating document, camera and microphone icons, soft pastel palette, clean shapes, white background, no text, no people
The prompt and the model decide the output; bigger models and settings cost more credits. These notes come from what worked, and what did not, in our runs.
Times are end to end on our GPU (an RTX 4060 Laptop GPU, 8 GB), model loading included, before any jobs ahead of yours. "Estimate" marks an option we have not measured yet.
| Option | Credits | Typical time | Slowest seen | What to expect |
|---|---|---|---|---|
| Thumbnail · 1280x720Recommended | 1 | 59 s | 59 s1 run | YouTube thumbnail size. Measured once: 35.9 s plus 23.5 s model load. |
| Square · 1024x1024 | 2 | 1 min 6 s | 1 min 6 s1 run | Posts and illustrations. Measured once: 42.2 s plus 23.5 s model load. |
| Poster · 1024x1536 | 4 | 3 min 20 s | 3 min 20 s1 run | Tall poster. Slower because it fills the 8 GB card: measured once, 176 s plus load. |
Step-by-step recipes that use Image with text with other studio tools, with the credits each step costs.
You answer for your prompt and your choice of model and settings; the safety filter still checks every job, and a refused prompt costs nothing.
1 creditunder a minute on our GPU, plus any jobs ahead
You'll have 7 days to download it; then it's deleted.
Results are kept 7 days. Credits come back only if the job fails or never starts.
Reading the line…
Credits are held when you send a job and spent when the result is ready. They come back automatically if the job fails, is refused or has not started within 24 hours. Results are kept 7 days, or 48 hours after your first download, then deleted; a result that expires unused is not refunded. Pricing and refunds
Usually close, not always: our trial wrote 'PDD' for 'PDF'. Keep titles short and check before use.
No. The model only writes Latin letters reliably; Arabic came out as nonsense shapes.
Wallpaper for tall phone backgrounds without words; Image with text when you need a title or a flat graphic.
Thumbnail (1280x720), 1 credit.
Yes; the model is Apache-2.