Watercolour botanical study with a prompt built for Midjourney and DALL-E. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
4.9(34 ratings)444 copies
Updated By Site Admin
39 words · v1.0
Fill in the blanks · 1 variable
Midjourney promptReplace every highlighted token before sending
Botanical watercolour study of {plant} on cold-press paper. Loose washes, visible paper grain, delicate ink outlines, a few unpainted areas for light. Scientific illustration accuracy, muted sage and ochre palette, generous white space. No text, no vase, no background. --ar 4:5 --style raw --stylize 100
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.
How to use this prompt
1
Open Midjourney and start a new chat. Paste the prompt exactly as written.
2
Replace each placeholder ({plant}) with your own details. Leave the instructions and the output format untouched.
3
Add one concrete example or data point if the model's first answer is vague. Specific input produces specific output.
4
Run it once, then ask for a single revision with a specific critique rather than regenerating from scratch.
5
Review the result. Model licence, likeness and trademark risk, and the image at 100% before publishing.
Worked example
This is the kind of input the prompt expects and the shape of output it produces. Your result will differ with the model and the details you supply.
Example input
Plant: a monstera leaf
Example output
The generated image should show the subject at the described angle with a single dominant light source, realistic material texture and clean negative space for type. Review at 100% for hand and text artefacts. If the composition is right but the light is flat, keep the seed and increase the direction of the key light rather than rewriting the whole prompt. If the style is right but the crop is wrong, change only the aspect ratio.
Tips for a better result
Lead with subject and light, then add style, then parameters. Order changes the result.
Iterate one variable at a time and save the seed when a composition works.
Always check hands, text and background edges at full resolution before delivery.
Change one variable at a time and compare the outputs; it is the fastest way to learn what this model responds to.
Common mistakes
Stuffing forty keywords into one prompt and hoping the model averages them well.
Copying a living artist's name or a competitor's protected character.
Using a generated image commercially without checking the model's licence terms.
Verified Knowledge · FAQ
Questions about this prompt
Practical answers about running the watercolour botanical study prompt.
Related prompts
Same job, a different angle — or the next step in the workflow.
Moody book cover concept with a prompt built for Midjourney and Flux. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
Minimal product packaging concept with a prompt built for Midjourney and Flux. It supplies context, constraints and an output contract, then asks the model to surface assumptions and gaps. Copy it, fill the variables and treat the result as a structured draft, not a final answer.
This copy-ready image prompt helps you sticker sheet with consistent style with fewer blank-page decisions. Paste it into DALL-E and Leonardo, fill the variables, and you get a structured first draft you can edit. It is written for repeatable results and tells you what to check before publishing.
DALL-ELeonardoMidjourney
4.8(78)524 copies
SA
Written and reviewed by Site Admin
Author & Platform Administrator
Administrator and lead editor at AIPrompt123, curating high-performance AI prompts, SEO/AEO/GEO strategies, and developer repositories.
Last reviewed 22 August 2026 · version 1.0 · tested on Midjourney, DALL-E, Stable Diffusion
Comments
Share what worked, what broke and which model you used. Comments appear after posting and are moderated for spam.