NEGATIVE PROMPTS · COPY & PASTE
The Best Negative Prompts for Every AI Model — Copy and Paste
JUNE 2026 · 10 MIN READ · AIPROMPTGENEER.COM
TL;DR — EXECUTIVE SUMMARY
Negative prompts are the most skipped and most impactful element of AI generation. This page gives you tested, copy-ready negative prompts for every major model: ChatGPT Image 2.0, FLUX.2 Pro, Midjourney v7, Kling 3.0, Seedance 2.0, Runway Gen-4, and LLMs. Use them as-is or stack with your own.
Why Negative Prompts Matter More Than Most People Think
A negative prompt is half the generation. Without one, the model fills every unstated preference with its highest-probability defaults: plastic-looking skin, flat even lighting, stock photo composition, generic facial expressions, and obvious AI artifacts. Defaults are the enemy of quality output.
A well-crafted negative prompt doesn't just block bad outcomes — it raises the floor of every generation. The same positive prompt produces measurably better output with a strong negative. Every single time. There is no exception to this rule across any model.
Universal Negative Prompt — Works on All Image Models
Start here. This covers the most common failure modes across every image generation model:
UNIVERSAL — ALL IMAGE MODELS
CGI, 3D render, cartoon, anime, illustration, painting, sketch, blurry, out of focus, bokeh overload, plastic skin, airbrushed skin, beauty filter, oversaturated, overexposed, blown highlights, underexposed, crushed blacks, watermark, text, logo, signature, username, deformed, mutated, extra limbs, extra fingers, missing fingers, fused fingers, disconnected body parts, floating limbs, malformed hands, bad anatomy, unrealistic body proportions, clone faces, duplicate subjects, two heads, multiple people (unless requested), flat lighting, harsh direct flash, ring light, studio backdrop (unless requested), stock photo look, generic pose
ChatGPT Image 2.0 — Negative Prompts
ChatGPT Image 2.0 handles negative prompts conversationally — add them at the end of your prompt or in a follow-up message.
ChatGPT Image 2.0
PORTRAIT / EDITORIAL
Avoid: CGI, plastic skin, airbrushed face, overexposed skin, beauty filter, fake smile, over-smoothed texture, flat lighting, ring light glow, stock photo pose, watermark, blurry background that looks artificial, extra fingers, malformed hands
PRODUCT PHOTOGRAPHY
Avoid: floating product, unrealistic shadows, fake reflections, cluttered background, text overlays, watermarks, lens distortion, overexposed surfaces, plastic-looking material texture, compressed artifacts
LIFESTYLE / UGC
Avoid: studio lighting, beauty filter, perfect symmetry, CGI quality, overly posed, stock photo energy, airbrushed skin, too-clean background, unrealistic skin, watermark
FLUX.2 Pro — Negative Prompts
FLUX.2 Pro has the highest prompt adherence of any image model — which means it also executes negatives precisely. Keep CFG between 3–5 for best results with negatives.
FLUX.2 ProFLUX.2 Pro Ultra
PHOTOREALISM — FLUX.2 PRO
CGI, render, artificial, plastic skin, airbrushed, beauty filter, watermark, blurry, soft focus, overexposed, flat lighting, fake bokeh, extra limbs, malformed anatomy, duplicate faces, low quality, compression artifacts, noise, grain (unless specified), oversaturated, oversharpened
ARCHITECTURE / ENVIRONMENT
People (unless specified), cars (unless specified), modern elements (for historic), anachronistic details, watermark, text, lens distortion, perspective errors, blown sky, overexposed windows, flat dull lighting, grey overcast (unless specified)
Midjourney v7 — Negative Prompts
Midjourney uses --no instead of a separate negative field. Append to the end of your prompt: --no plastic skin, watermark, text, extra fingers
Midjourney v7
MIDJOURNEY — PORTRAIT
--no plastic skin, airbrushed, beauty filter, watermark, text, extra fingers, deformed hands, malformed anatomy, blurry, oversaturated, flat lighting, stock photo, clone faces
MIDJOURNEY — EDITORIAL FASHION
--no casual, street wear (unless specified), messy hair (unless specified), bad posture, poor lighting, watermark, text, extra limbs, unnatural proportions, plastic skin, airbrushed
Kling 3.0 + Seedance 2.0 — Video Negative Prompts
Video models need identity-specific negatives more than image models. The biggest failure modes are temporal drift and morphing — not just visual artifacts.
Kling 3.0 ↗Seedance 2.0
AI VIDEO — HUMAN MOTION (ALL MODELS)
morphing face, identity drift, changing appearance between frames, inconsistent features, flickering, temporal artifacts, jerky unnatural movement, teleporting, cloned person, duplicate subjects, disembodied limbs, floating body parts, unphysical motion, watermark, text overlay, scene cuts (unless specified), freeze frames, black frames, distorted anatomy during movement
AI VIDEO — ENVIRONMENT / B-ROLL
flickering light, temporal inconsistency, jumping objects, unnatural physics, watermark, text, black frames, sudden cuts, distorted perspective, unnatural speed changes, reversed motion (unless specified)
Runway Gen-4 — Negative Prompts
Runway Gen-4
RUNWAY GEN-4 — CINEMATIC
amateur footage, handheld shake (unless specified), blown exposure, flat color, temporal flicker, identity drift, morphing, watermark, text overlay, abrupt cuts, freeze frames, distorted motion blur, unnatural physics, plastic CGI quality
LLM Negative Prompts — ChatGPT, Claude, Gemini
LLMs don't have a negative prompt field — you embed exclusions directly in the prompt or system prompt. These are the most impactful exclusions for common use cases:
COPY / BRAND WRITING
No filler phrases. No exclamation marks unless explicitly requested. Never use the words: "transform", "elevate", "curate", "journey", "innovative", "cutting-edge", "seamless", "robust", "leverage", "synergy". No introductory sentences explaining what you're about to do. No summarizing what you just wrote at the end. Do not start sentences with "I". No bullet points unless specifically asked.
FACTUAL / RESEARCH WRITING
No hallucinated statistics or citations. Do not fabricate sources. No hedging phrases like "it's worth noting that" or "it's important to consider". No repetition of information already stated. No vague qualifiers. No padding. Cite only what you can confirm. If uncertain, say so directly.
SEE MORE: The
Negative Prompt Library on the home page has 20+ copy-ready negative prompts organized by use case — photorealism, fashion, video, architecture, and more.
SEE MORE: The
Negative Prompt Library on the home page has 20+ copy-ready negative prompts organized by use case — photorealism, fashion, video, architecture, and more.
class="nl-cta">
More prompts. Every week.
Production-ready prompts, model guides, and workflow breakdowns — free forever.
SUBSCRIBE FREE ↗