KNOWLEDGE NOTESKnowledge Notes
Explore curated knowledge, course notes and methods, with their existing content and sources preserved.
This index lists complete English editions. Additional Chinese notes and bilingual updates remain available in the Chinese index.
350knowledge notesSynthesis of aesthetics / democratization of creation from 3 perspectives. Xiaohongshu vibecoding aesthetic philosophy (models don't matter, aesthetics do + Stanford aesthetics course 5 units + 3 Kimi 2.6 tuning tricks for 1:1 replication + three terms Hero/Shader/Three.js + Pretext 21 million views + 80→100 make-or-break line + 3 tiers of realm)/ xhs-vibecoding-ai-web (3D interaction + AI web pages)/ newtype Dan Koe creator story ($3K → $4.2M) + Trinity Visual Learning. Covers aesthetics as the primary productive force, AI democratizing creation, 3 tiers of realm, and the creator economy
Integration of "AI self-media + content engineering" from the perspectives of 7 authors. Lao D (domestic, no scientific internet access + 2 million views on Douyin) / Wang Kai (overseas 6-platform SOP + matrix operation + going-global infrastructure) / Huang Yihe (non-technical independent products + global merchant route) / Xiaohongshu vibecoding (aesthetic philosophy + democratized creation) / Yuzijiang (AI comic drama agency team system + Hongguo Theater revenue share) / Lao Zhang (reverse-engineering X recommendation algorithm source code) / **zara Zhang Zala (Build in public + Inbound + 260,000 followers + 0 ads + ≤30 min per piece + 6 returns more valuable than money)**. Covers goal divergences, consensus, debates over AI writing purity, single-platform deep cultivation vs multi-platform matrix, tool stack comparison, and monetization paths
A synthesis of AI video generation SOPs from 4 perspectives. Caviar Agency (5-step AI comic drama process + 9-column storyboard sheet + 6 major camera movements + 5x revenue share on Hongguo Theater)/ Xiaohongshu vibecoding (5-step 1-to-1 replication for AI outfits + canvas-based operation + 6-step cinematic AI web pages)/ Wang Kai (SillyTavern video Phase 1-7 engineering template + Components/Compositions layering + Jimeng CLI premium membership)/ Lao D (L05 text-to-image → image-to-video → lip sync + L10 HeyGen digital human 5-tool combo + 30 languages). Covers tool stack comparison for Jimeng / Vidu / Tongyi Wanxiang / HeyGen / ElevenLabs / CapCut
Explains the applicable scope of AI video last-frame relay, prompt duration, final decoded-frame extraction, and stitching conditions; adds frame-by-frame and audio-enabled checks, retains the 31-second historical case, and avoids promising that arbitrary segments will have no jumps.
Generative models resist "continuous subtle camera shake" (Veo hits 1/3 / Seedance locks to a static frame) → stop rolling the dice; do post compositing: 10% upscale + triple-frequency sine dynamic crop + segmented amplitude envelope (large when walking / small when standing still / halved when holding breath). Includes zero-dependency script, acceptance parameters, quantitative self-check method, Veo vs Seedance behavior comparison, and five core principles for POV prompts. Tested across 10 rounds and 40+ generations on StoReel; two deliverables passed acceptance.
Highlights from Will’s practical notes on AI visual generation: breaking down "using AI to produce visual assets" into 6 actionable task categories, each with reusable prompt skeletons, rationales, and common pitfalls. ① Image enhancement (turning blurry portraits into 4K / sharpening general images): relies on image-to-image detail reconstruction via Gemica/Gemini; the key constraint is "lock identity and composition, only fill in details, do not add new elements"; for portraits, use camera parameters (85mm f/1.4 / Sony A1) to force photorealism. ② 3D icons & IP design: AI has extremely strong recognition of 3D textures, so finding reference images > writing prompts (50% time spent finding images + 50% debugging); provides ready-made prompt templates for Airbnb isometric icons, soft vinyl blind box figures (Kakao Friends style), Apple skeuomorphic icons, and highly stylized 3D avatars. ③ KV key visuals: two approaches — "reskinning" (replacing the IP on a mature reference image, adjusting poses/environment to avoid plagiarism) and "original creation" (hand-drawn line art + AI stylization), including pitfalls such as using a 1:1 head-to-body ratio to prevent AI from switching to realistic human proportions. ④ Stylized illustrations & state graphics: one sentence to make AI produce a set of 6 stylistically consistent onboarding illustrations (lock color palette and brushwork, loosen shape constraints). ⑤ Visual remix reconstruction: take one dimension from each of multiple images (shape from image 1 + texture from image 2 + lighting from image 3) and fuse them into a custom visual, including a 4-step iterative practical case for in-car HMI. ⑥ Visual reference dimensions: 6 "image breakdown checklists" for photography/illustration/3D/brand/character/product photography, teaching PMs to break a reference image down into describable keyword dimensions. Target readers: PMs building AI products who need to produce icons/KVs/illustrations themselves; industry jargon is explained in-line, and prompts are retained in both Chinese and English.
November 2025 Caviar Agency AI Comic Drama Section 1 live class. Complete production workflow from script to finished video (script generation → storyboard table → asset library → image fusion → first and last frames → video), Hongguo Theater monetization path, six major camera movement concepts of push, pull, pan, track, follow and orbit, Jimeng/Vidu tool stack, character consistency and three-view asset library, detailed prompt description list (full checklist of body type/hairstyle/clothing/accessories/painting style), complete script case of "Recruiting Team Members in the Apocalypse, I Only Pick the Most Useless"
dontbesilent (Old D) 2026-05 AI Self-Media Course, a complete 13-lesson learning path. It fully covers the entire production chain for users in mainland China who do not use scientific internet access and have no coding background to do self-media with AI, including model selection, the three layers of prompts (meta/system/user), the essence of RAG knowledge bases, AI copywriting imitation SOP, zero-code agent usage with Claude Code, LobeChat for blogger style imitation + conversation branching + Artifacts, HeyGen digital human translation + Tongyi Wanxiang wan2.2 animate character replacement, one-click Xiaohongshu publishing with Claude 4.5 + Playwright, and Claude Skill engineering for system prompt management.
20 curated essential pieces from the Nielsen Norman Group knowledge base on content strategy and web writing, organized around three core axes: ① Content governance and process — Content Strategy is the high-level plan that precedes tactics (four phases: Plan, Create, Maintain, Unpublish); Content Strategy vs UX Writing (the former governs processes while the latter writes copy, with a 9-dimension division of responsibilities), Content Design, Content Inventory (listing all assets) vs Content Audit (assessing quality; inventory first, then audit, with audits conducted at least every 3 months), integrating Content Standards into design systems (global + specific, reviewed annually), 3 intranet content management models (centralized/decentralized/hybrid), 5 types of content user stories in Agile (including content research Spikes), and Information Architecture (IA) vs Sitemap. ② How to write content people will actually read — People primarily read online via Scanning (13 years, 500+ participants, 750 hours of eyetracking data); 5 classic scanning patterns (F-pattern/Spotted/Layer-Cake/Commitment/Lawn Mower) plus new patterns (Pinball: 158 jumps in 14 seconds; Love-at-First-Sight SERP: 20% of users view only one result); the Inverted Pyramid with conclusions placed first; 7 methods for concise writing (including Kill Your Darlings); 5 layout approaches for long-form content (summaries/bold highlighting ≤30%/key points/callouts/visuals); microcopy (<3 sentences) with the 3I framework (Inform/Influence/Interact) + 3C framework (Clarity/Concision/Character); 4 dimensions of Tone of Voice (funny-serious/formal-informal/respectful-disrespectful/enthusiastic-matter-of-fact). ③ How to validate — Content testing uses open-ended information-finding tasks + open-ended follow-up questions; Eyetracking setup (fixation maps: 8–12 participants; heatmaps: 39 participants; Tobii Spectrum). Target readers = product managers; jargon is explained in-line; decision-oriented (when to use/how to choose/counterexamples).
This entry archives a local textual research report from June 2026, distinguishing between industrial background, internet labels, rumors, and location-based marketing speculation; it does not judge residents on the basis of regional labels.
A complete end-to-end SOP for mass production of product videos. Phases 1–7 engineering: directory skeleton → reference video analysis → real asset scraping → writing the Skill → first video → three video types + Jimeng mixed cuts → scaling. Demonstrates the core principle: "use code for precise effects, use text for broad rules."
Content recorded across 360 posts + community operation practice: 1135 posts over 3 years of Zsxq operation, using Zsxq as a wiki, content ecosystem, 25 yuan per person referral commission, guest titles, community insights, personal IP, private domain traffic, KOL collaboration
Complete SOP for 1-to-1 replication of AI outfit videos by Xiaohongshu vibecoding creators. Text-to-image reverse prompt engineering + image-to-image fusion (clothing × model) + motion transfer cropping + batch node generation + keyframing in editing. Paired with the Vibe Marketing skill for batch video production (see [[xhs-vibecoding-ai-tools]]). This wiki is a small aggregation of content for 4 types of video production (it is a standalone wiki because AI video replication is a very specific workflow with independent teaching value)
21 healing works by Xiaohongshu vibecoding creators. **Huahua Land series** (emotion diary + free placement + nighttime fireflies + New Year wishing meteors) + **Cyber Garden** (worker energy field + flower language diary) + **AI News Planted in the Cyber Garden** (antidote to information anxiety + cherry blossom new products/iris multimodal/dandelion academia/lily safety policy) + **Natural Planet series** (tracking of 2 million pollen grains + 21 soundscapes of dancing butterflies and chirping insects + bird song planet migration trajectories + undersea garden corals + flower language world + Earth flower language) + **Dreamcore Healing Puzzle** (one-click generation with Minimax Pro). **Use vibecoding to turn healing vibes and nature into an explorable world**
Understand low-burden output, positioning, and learning in public through Zara Zhang Zala’s historical cases on Xiaohongshu and across platforms; includes direct chapter links and short exercises, distinguishing follower self-descriptions, tool use, and effect boundaries across different periods.
