Unverified50% confidenceFactExact time
Prompts are typically composed of descriptive words for subject, style, image quality, and composition plus weighting syntax; negative prompts are used to exclude unwanted elements.
1
Sources
50%
Confidence
Long-term
Relevance
10/28/2026
First Seen
Sources
October Open-Source Gem: The Complete Guide to Local Stable Diffusion Deployment
bilibiliAIGC高手10/28/2026
Related Entities
Related Claims
UnverifiedA descriptive prompt is a piece of text that describes the target category or its visual features in natural language, used in zero-shot inference to construct the text embedding corresponding to the category and match it against image features.72% similarUnverifiedA negative prompt is a control mechanism in T2V and image generation models used to explicitly specify 'what not to generate'; TIDE generates both positive and negative prompts to constrain the generation space more completely.68% similarUnverifiedStructured Prompt means breaking a task down into explicit fields and constraints rather than describing it casually in natural language.64% similarUnverifiedA prompt can be split into two categories: pure product content (tone, wording, few-shot examples, fallback scripts, pricing explanations) and behavior logic that is more like code (tool descriptions, output format, guardrail instructions, stop instructions).64% similarUnverifiedA controlled vocabulary is a predefined, limited and semantically clear set of exclusion reason labels rather than free text; its benefits are that exclusion records can be aggregated for analysis and compared across cases, and vague wording is avoided.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1108060API
curl https://kongchang.com/api/v1/knowledge/claims/1108060MCP
get_claim(id=1108060)