Midjourney prompts work better when you describe materials, not adjectives
tisch_eins · x · 2026-07-20
The post argues that prompts often fail on a single vague word, especially adjectives like “beautiful.”
It recommends replacing vague descriptors with concrete materials and visual structure. Example:
- Weak: “a beautiful mosaic portrait”
- Strong: “[subject] as a Byzantine gold mosaic, tiny glass tesserae, shimmering gold ground, bold dark outlines, aged grout lines, richly detailed --ar 5:4 --v 8.1”
The takeaway is simple: describe what the model should render in terms of materials, texture, and construction details instead of generic praise words.
More from Multimodal
- FLUX.2 Klein Drifts Hard on Character Expressions While Free Gemini Holds Likeness — wacomlover · 2026-09-11
- Tencent Hunyuan releases AuK code and weights on GitHub with ComfyUI and fine-tuning support — aigclink · 2026-09-11
- Tencent open-sources AuK, a unified 1.5B speech generation and editing model — aigclink · 2026-09-11
- Creator turns Bahamut vs Tiamat rivalry into an AI cinematic battle with Midjourney, GPT Image 2 and Seedance — azed_ai · 2026-09-11
- invideo launches AI agent-powered editor to automate repetitive editing tasks — azed_ai · 2026-09-11
- fable 5.1 recreates The Starry Night with 256,157 JavaScript brush strokes — cedric_chee · 2026-09-11