Peter Yuan
ImageJapanese Ukiyo-e Woodblock Art
Turn text descriptions or photos into images with the traditional character of Japanese ukiyo-e woodblock prints. Preserve a person’s core identity, posture, and relationship to the setting while translating poetry, stories, and the mood of nature into clear visual narratives. Whether you’re creating a portrait, landscape, seasonal scene, or vertical image for social media, the composition will use an appropriate aspect ratio and visual focus. The artwork emphasizes asymmetrical composition, layered foreground, middle ground, and background, generous negative space, diagonal visual guidance, and expressive moments of movement and emotion. Natural atmosphere—such as rain, snow, mist, wind and waves, moonlight, mountains and water, pine and bamboo, and cherry blossoms—is highlighted without meaninglessly piling on symbols like samurai, Mount Fuji, or shrines. Photo inputs receive a moderate simplification of realistic lighting while preserving recognizable facial features, age, body type, clothing, and posture. The final image features clear, flowing black outlines, flat color blocks, restrained traditional tones such as indigo and ochre, and the texture of paper fibers, woodblock impressions, and hand-printed registration. It avoids photorealism, modern anime, 3D rendering, cyberpunk, and heavy oil-paint effects. Unless explicitly requested, no text, titles, captions, or watermarks will be added.
ImageEastern Philosophy Comics
Turn a sentence, philosophical idea, piece of classical prose or poetry, fable, everyday question, scene description, or uploaded photo into a simple, quiet, original comic illustration with an Eastern philosophical sensibility. The artwork centers on black-and-white ink lines, symbolic figures, generous negative space, and minimal environmental elements, allowing abstract ideas to emerge naturally through gestures, key objects, and spatial relationships rather than lengthy textual explanation. For abstract concepts such as “自我消耗,” “自由,” and “沉没成本,” as well as Zen koans, Tang and Song poetry, and historical stories, the skill distills the underlying tensions and meaning, then chooses a suitable single-panel composition or multi-panel narrative to express themes such as loneliness, choice, desire, and impermanence. Figures, clothing, and settings are simplified to suit modern or classical contexts while preserving a clear, two-dimensional comic style and visual metaphors. When you upload a photo, it can be redrawn as a minimalist Eastern line-art comic while preserving recognizable features, posture, clothing, and the main compositional relationships, rather than simply applying a filter. Text is not added by default; when needed, specified text can be retained, a small amount of dialogue added, or the aspect ratio, panel count, or low-saturation colors adjusted. Realistic, 3D, anime-inspired, and complex commercial illustration styles are avoided.
ImageDark 3D Literary Characters
Transform characters from *Romance of the Three Kingdoms*, *Water Margin*, *Journey to the West*, *Dream of the Red Chamber*, and other Chinese classical works into polished 3D cartoon game characters that remain recognizable without written labels. Whether depicting generals, warriors, monks, scholars, women, immortals, or monsters, the skill combines each character’s identity, stage of life, and defining experiences with visual designs grounded in the historical setting—reducing timeline errors, lookalike characters, and cultural mismatches. You’ll receive a complete character-recognition-focused design plan covering silhouette, signature weapons and accessories, clothing materials, color palettes, pose and expression, environmental mood, and differentiation from similar characters. It also accounts for common image-generation inaccuracies involving ancient Chinese clothing, weapons, and character types. When the source material is uncertain, references are checked first to determine the appropriate period and visual direction. The skill supports both character illustration and scene-based requests. It can produce reusable, copyable image-generation Prompts, specify image dimensions, and review the result for period accuracy, key symbols, colors, cultural traits, pose and structure, and overall recognizability—making corrections and iterations when needed. It is suitable for classical literature character concepts, game character development, visual design, and Chinese-style AI image generation.
AI Lipstick Try-On
Upload a clear, front-facing portrait. AI analyzes your face shape and skin tone, then matches 1–3 suitable shades and brands from a built-in database of 400+ real lipsticks. GPT Image 2 generates a 1:1 front-facing try-on image with the selected shade applied to your lips, your face reproduced 100%, and a bare-face base to highlight the color—so you can see the result clearly and decide whether to buy.
ImageThermal Receipt Poster Maker
Turn life records, travel memories, relationship moments, birthday feelings, unemployment updates, or even a single sentence into a receipt-style poster with an authentic thermal-paper texture. Your content is organized into visual details such as the date, location, mood, daily entries, a memorable quote, and a footer, giving abstract everyday moments a “record receipt” of their own. It preserves the dates, numbers, proper names, and key facts you provide, without inventing measurements such as prices, step counts, or temperatures. When information is incomplete, it fills out the layout in a restrained, design-conscious way. Quote copy leans toward dry humor, breathing room, and conversational language, avoiding an advertising tone and generic inspirational slogans. By default, it follows the input language to create a Chinese or English version, and it also supports a bilingual version when explicitly requested. After the text is confirmed, it can generate vertical AI images suited for Xiaohongshu, Instagram, Stories, or Reels, while checking text clarity, layout proportions, whitespace, and the look of thermal printing. It is ideal for sharing everyday updates, travel memories, and personal mood records.
ImageModern Chinese Era Visuals
Transform titles, themes, or graphics into visual designs inspired by modern Chinese eras, suitable for book covers, posters, cards, illustrations, typography, and social media graphics. Simply provide the text, target era, design format, and aspect ratio to receive a visual concept tailored to your theme. If no ratio is specified, a portrait cover composition can be used. Supports a range of styles from the 1920s–30s Republic of China period and the 1940s through the 2000s, including Eastern Constructivism, War of Resistance woodcut, revolutionary realism, understated literary design, humanistic minimalism, and digital visual styles. Each era-based style presents a distinct design language through its color palette, composition, typography, graphics, and print texture—for example, geometric display lettering, woodcut marks, limited-color flat fills, asymmetrical layouts, paper grain, and balanced negative space. Whether you need a literary book cover, an era-themed poster, or a simple Chinese title design, you can evoke the aesthetics of the corresponding period while keeping the text clear and the composition clean. Supports common aspect ratios including 1:1, 2:3, 3:2, 4:3, 16:9, and 9:16, making it suitable for publishing visuals, exhibition promotion, content graphics, and personal creative work.
ImagePhoto & Text Mosaic Art
A studio for transforming and generating mosaic art. Supports more than 15 historical and contemporary mosaic styles, including Byzantine, Soviet Socialist Realism, Gaudí Trencadís, Islamic Zellij, Ancient Roman, Renaissance, Mexican mural, Art Deco, and contemporary abstract styles. Use it when you want to transform an image, photo, or portrait into a mosaic style; generate mosaic artwork from a text description; explore different mosaic styles; or work with concepts such as mosaic,碎瓷砖拼贴, or glass tessellation. Users can specify a style, or let AI recommend the most suitable mosaic style based on the image content or scene description. Built-in full-frame, no-exceptions mosaic processing handles high-realism risk areas such as people's eyes, skies, metal, and glass.
ImageCinematic Quote Posters
Turn a portrait and a quote into a vertical quote poster with a cinematic narrative feel. The person’s facial features, hairstyle, and identity are kept as consistent as possible with the reference photo, while the quote’s mood shapes scenes such as an interview, at-home conversation, courtroom statement, seaside monologue, rainy-night street, or retro Hong Kong style. Ideal for character quote graphics, mood posters, and social media content. Choose a preset template or customize the scene, clothing, pose, and atmosphere. You can also use speaking lip shapes, Chinese-English bilingual text, classic layouts, subtitle styles, minimalist styling, and Hong Kong-inspired color tones, with output in 3:4, 9:16, or 1:1 ratios. Longer quotes are condensed and line-broken for poster presentation, keeping the text concentrated near the bottom of the image, away from the person’s face, and clear and readable. The final deliverable is an AI-generated cinematic quote poster, with the selected scene, text style, and aspect ratio noted. Because the text is rendered directly by AI, complex or lengthy quotes may occasionally contain incorrect characters. If the text is inaccurate, try shortening the quote or request a new generation.
ImagePhoto to Risograph Texture
Convert user-uploaded photos or images into high-quality simulated prints with the authentic texture of Risograph printing, independent publications, and ZINEs. Reimagine the visual medium through color separation, spot inks, halftone dots, registration shifts, ink overprinting, and paper texture. By default, the original subject, composition, people’s identities, and key content are preserved; only the visual presentation is changed.
ImageMature American 2D Animation
A no-setup visual transformation skill that automatically turns reference images or text descriptions into a mature, adult-oriented American 2D TV animation aesthetic—with graphically simplified characters, clean outlines, flat color blocks, richly detailed environments, cinematic composition, and emotionally mature storytelling. No animation titles or style terms required—just generate.
ImageReal Handwriting Images
Turn user-provided Chinese or English copy, handwriting details, paper, writing tools, environment, and photography requirements into prompts for highly realistic “real handwriting” images. It can also directly call image generation to create the final image. The core goal is to avoid the look of font libraries, calligraphy artwork, or obvious AI generation, so the text appears to be genuinely written by a specific person, at a specific time, on a specific surface. Trigger scenarios: handwriting, handwritten letters, handwritten images, handwritten notes, note messages, letter paper, handwritten diaries, handwriting styles, and generating images from handwritten copy.
WriteHuman-Voice WeChat Writing
Turn a trending event, social phenomenon, workplace or relationship topic, personal experience, industry observation, product material, or existing draft into a WeChat Official Account article with a clear position, genuine emotion, and strong shareability. It doesn’t stop at the safe, even-handed “everyone has a point.” Instead, it helps you find an angle that fits your target readers, identify the real conflicts and pain points, and use specific scenes, everyday details, and memorable judgments to make the article sound like it was written by a real person with experience and preferences—someone who also acknowledges the limits of their understanding. Along with a publish-ready draft, it also organizes the creative decisions, title directions, and article’s core points. It prepares authorial responses for real-world comment scenarios, including challenges to the facts, opposing views, personal experience sharing, and quotes taken out of context, making it easier to handle discussion after publication. For trending topics, controversial events, and high-risk subjects such as law, medicine, and finance, it distinguishes known facts, reasonable inferences, and the author’s judgments, avoids fabricated information, and flags areas that still need sources or verification. It’s suited to WeChat Official Account writers, independent media editors, and content teams creating social commentary, workplace perspectives, relationship and emotional opinions, personal growth topics, and industry commentary. It’s especially useful when you want to move beyond detached “both-sides” writing and AI-sounding prose without relying on personal attacks, exaggerating facts, or creating needless conflict to gain attention.