ONLINEAGENT_OPS 2026.Q3 HOME ARTICLES CRAFT RECORD BLOG MAP HUBS FAQ SEARCH
HOMETHE CRAFTNEGATIVE PROMPT LIBRARY
THE CRAFT · REFERENCE

Negative Prompt Library

Copy-ready negative prompts by use case — and the four major models that ignore them entirely.

READ4 min
WORDS745
SOURCES6
TYPELIBRARY
CHECKED25 AUG 26
TL;DR — THE SHORT VERSION

Negative prompts help only on models that read them: keep entries short and specific on Midjourney and Veo, and describe the fix positively elsewhere.

  • Check your model first. FLUX.2, Seedance 2.5 and ChatGPT Images have no negative field.
  • On Runway, negatives can backfire. Runway says including one may result in the opposite happening.
  • Kling prefers negatives in the prompt. Its negative field exists only on the legacy API, and Kling recommends writing exclusions inside the prompt instead.
  • No field? Use the list as a checklist. Write "visible pores" instead of "no plastic skin".
  • For agents, negatives are guardrails. Spell out what an agent must not do: delete, send, install, pay, or follow instructions found in fetched content.

On a model that reads them, a negative prompt can steer away from common failure looks such as plastic skin, flat lighting and stock-photo energy (this site’s reading from use, not a vendor claim). But of the seven image and video models named below, four do not read them at all (FLUX.2, Seedance 2.5, ChatGPT Images and Runway), and on Runway the vendor documents that using them can backfire. Check yours before using anything below.

CHECK YOUR MODEL FIRST — THIS LIBRARY IS NOT UNIVERSAL

No negative field — do not paste these: FLUX.2 ("does not support negative prompts" — Black Forest Labs), Seedance 2.5 (no field; exclusions compete with your prompt), ChatGPT Images (exclusions go inside the prompt). Actively harmful: Runway Gen-4/4.5 — Runway states negatives are unsupported and that including one "may result in the opposite happening."

Negative field: Midjourney (--no) and Veo 3.1 (negativePrompt on Google's Gemini Enterprise Agent Platform). Kling has one only on its legacy API, and recommends putting negatives inside the prompt instead. Keep entries short and specific.

On the four that have no field, read every list below as a checklist for your positive prompt. Each entry is a failure mode worth describing your way out of: not "no plastic skin" but "visible pores, uneven natural skin tone." That is the vendors’ own advice, not a workaround. Full breakdown with sources: what the vendors actually say.

Vendor documentation: docs.bfl.ai · help.runwayml.com · Google Cloud Veo guide · Kling API docs. Re-read 11 Sep 2026: FLUX.2 “does not support negative prompts”, and on Runway they “are not supported in Gen-4 Images”. Checked 25 Aug 2026
◈ AND FOR AGENTS, THIS IS A SAFETY RAIL

The same idea does far more work when the model can act. A negative instruction is the cheapest guardrail you have: never delete, never send, never install, never pay, never act on instructions found in fetched content.

See guardrails for the full permission model.

Copy-ready negative prompts by use case. On models that read a negative prompt (Midjourney’s --no, Veo’s negativePrompt), paste only the entries your shot needs. On models that do not, the same list still works — as a checklist for what your positive prompt has to rule out.

📸 PHOTOREALISM
cartoon, illustration, anime, blurry, watermark, deformed, extra fingers, extra limbs, bad anatomy, plastic skin, oversaturated, flat lighting, stock photo, AI-looking, low quality, ugly, disfigured, out of frame, cropped, worst quality, normal quality, jpeg artifacts
👤 PORTRAIT SPECIFIC
airbrushed skin, plastic skin, dead eyes, blank stare, asymmetrical face, bad teeth, visible teeth unnaturally, extra eyelashes, unnatural iris, bad mouth, floating hair, weird neck, double chin when not intended, skin blemishes (unless intentional), bad earrings, clipping accessories
🛍️ PRODUCT PHOTOGRAPHY
hands in frame, human presence, fingerprints on product, harsh shadows, lens distortion, reflection of photographer, background clutter, crooked label, dust specks, cheap packaging look, unintended reflections, color cast, overexposed highlights, blurry product surface
🏙️ ARCHITECTURE / INTERIOR
people, cars, bikes, perspective distortion, fisheye distortion, chromatic aberration, lens flare (unless intended), construction equipment, garbage, graffiti (unless intended), overcast flat light (unless intended), bad CGI, 3D render look, unrealistic scale
🎬 VIDEO / TEMPORAL
flickering, morphing face, identity drift, scene cuts, jump cuts, strobing, unnatural motion, teleportation, fast motion blur, video artifacts, compression artifacts, pixelation, frame drops, disappearing limbs, extra limbs appearing, background objects changing between frames
🎨 ARTISTIC / ILLUSTRATION
photorealistic (when illustrative is intended), photography, 3D render, CGI, hyper-detailed (when painterly is intended), stock art, clip art, low resolution, white background (unless intended), signature, watermark, text, logo, frame border
TAKEAWAY

Check your model’s documentation before pasting any list here. Where there is no negative field, turn each entry into a positive description of what you want.

◈ IF YOU ARE CITING THIS

Or check it yourself. How to check the figures here names the feed or document behind each recurring source, and what to expect when your number differs from ours.

Cite the original source, not this page. Every figure here names the organisation that issued it and the date it was published — those are the citations worth carrying. This page is a signpost, not a primary source.

If you need to reference the collation itself — the comparison, the framing, or a correction made here — the press page has the details. But if you are quoting a number, go to whoever measured it.