Peter Wang
108 posts

Peter Wang
@PeterWang83707
AI图像创作者 | ComfyUI / Flux 每日分享 欢迎交流提示词与工作流 ✨ AI Image Creator | ComfyUI & Flux Daily generations • Prompt & workflow talks welcome ✨






GPT image 2 on chatgpt Prompt: Use the uploaded character reference image as the strict identity and outfit reference. Preserve the reference character’s: - face identity - facial proportions - eye shape - nose - lips - skin tone - hairstyle - hair color - visible hair accessories - overall recognizable vibe - outfit and styling shown in the reference image Do not hardcode any specific character traits that are not present in the uploaded reference. All identity, hairstyle, accessories, and clothing details must be inferred directly from the uploaded reference image. Create a high-quality mixed-style vertical portrait showing: 1. a realistic full-body version of the uploaded character/person 2. a black hand-drawn doodle-shadow version of the same character/person on the wall beside them Core concept: The real person and their doodle-shadow are doing a playful mischievous pose together. The real person performs a cute realistic version of the pose, while the doodle-shadow performs a much more exaggerated, chaotic, cartoonish version of the same pose idea. The mood should feel cute, playful, mischievous, stylish, funny, and social-media-friendly. Real person: - Must remain realistic and photogenic - Must wear the same outfit style and key visible details from the uploaded reference image - Do not replace the reference styling with unrelated fashion - Expression should be cute, slightly confused, mildly embarrassed, playful, as if thinking: “Why am I doing this with my shadow?” - The real person should not stand stiffly - The real person should actively participate in the pose, but in a natural realistic way Doodle-shadow: - Must be a black hand-drawn sketch version of the same person, drawn directly on the wall - Not a realistic second person - Not a normal physical shadow - Not a full-color anime character - Black sketch line-art only - Should resemble the person through hairstyle silhouette, accessories, outfit silhouette, and pose structure - The doodle-shadow should look more energetic, sillier, and more chaotic than the real person - Add manga-like motion lines, hearts, stars, sparkles, and comic marks around the doodle if helpful Random mischievous pose rule: The pose must NOT be fixed. For each generation, invent a new playful mischievous pose for both the real person and the doodle-shadow. The real person and the doodle-shadow should share the same general pose idea, but they do not need to match perfectly. The real person performs a cute realistic version. The doodle-shadow performs a much more exaggerated, chaotic, cartoonish version. Do not repeatedly use pointing poses. Do not repeatedly use finger-gun poses. Do not repeatedly use the same standing pose. Do not always make both figures simply point at each other. Create a different mischievous pose each time. Possible pose directions are loose inspiration only, not a fixed menu: - playful idol pose - silly dance pose - leaning sideways with one arm curved overhead - making a big heart pose - cheeky wink pose - hands near cheeks in a cute teasing pose - exaggerated “ta-da!” pose - mock surprise pose - playful running-in-place pose - mischievous tiptoe pose - arms stretched in opposite directions - pretending to sneak away - cute troublemaker pose - dramatic overreaction pose - goofy victory pose - playful balance pose - playful peekaboo pose - shy but mischievous pose - cute overconfident pose The final pose should feel fresh, cute, mischievous, and slightly chaotic. The real person should look like they are reluctantly playing along. The doodle-shadow should look like it is having way too much fun. Composition: - vertical 4:5 or 9:16 - show the real person in full-body or nearly full-body framing - place the real person on one side of the frame - place the black doodle-shadow on a clean wall beside them - the doodle-shadow should be roughly the same height or slightly taller - keep enough space around both figures so the full pose is visible - the connection between the real person and the doodle-shadow must be clear at a glance Background: - simple clean indoor studio wall or minimal room corner - white, cream, or pale gray wall - clean floor - soft natural sunlight patch or gentle wall shadow allowed - keep the background uncluttered Lighting: - soft natural studio lighting - bright, clean, polished, playful mood - keep the real person’s face clearly visible Style quality: - realistic human photography - black hand-drawn doodle-shadow on wall - matching mischievous pose interaction - strong identity resemblance - outfit and styling faithfully based on the uploaded reference - cute and stylish mixed-media portrait - clean composition - social-media-friendly - no obvious AI artifacts Negative prompt: hardcoded blue hair when not in reference, hardcoded cloud clip when not in reference, hardcoded fish clip when not in reference, hardcoded school uniform when not in reference, outfit change unrelated to reference, realistic second person, normal reflection, normal shadow only, solid black monster shadow, horror shadow, creepy shadow, full-color illustration, cartoon human, anime human, weak resemblance, unrelated sketch character, messy wall, cluttered background, repeated pointing pose, repeated finger-gun pose, same pose every time, fixed pose, boring mirrored pose, stiff pose, identical pose repetition, real person not matching shadow pose, text, watermark, logo, distorted body, extra limbs, extra fingers, bad hands










刚把圣斗士角色设定稿的设计方法做成了线稿角色设计 Skill 💎Character design sheets inspired by Saint Seiya, featuring technical blueprint aesthetics and magazine-style editorial layouts. 🍓🍓🍓用 GPT Image2 跑了紫龙、冰河、瞬、一辉—— 每个角色都保持视觉一致性,但姿势、配色、文字布局都是定制的 你们做设计时,会把自己的方法"系统化"吗? 还是每次都重新摸索?🤔 评论区聊聊: 1️⃣ 你觉得AI设计最大的价值是"效率"还是"创意"? 2️⃣ 你会为自己的设计风格建立"方法论"吗? 3️⃣ 想看我用这套理念做什么题材的设计?(点赞最高的我来安排设计) #AIDesign #CharacterDesign #DesignThinking #DesignWorkflow #GPTImage #圣斗士


不是啊? ChatGPT 5.6 sol审核变严了是体感上的确认啊 但是下面这种 韩漫御姐 OL 群像风 怎么就能整出来?! 感觉是因为真人和动漫的画风区别? 兄弟们拿提示词去试试看是被拒还是能出图?👇


Good morning, Chairman. prompt:promptsref.com/tool/AI-Image-… Create a vertical 9:16 modern-office group portrait containing exactly seven clearly adult women, approximately 23 to 30 years old. Two women stand in the back row and lean subtly toward the center, while five women sit closely together on pale office chairs or a bench in the foreground. Every subject looks naturally toward a camera positioned low and directly in front of them. Preserve seven distinct faces with believable facial variation, slight asymmetry, subtly different smiles and individual head angles. Do not create repeated faces or a single cloned beauty template. Their outfits are coordinated without being perfectly identical: warm-white, ivory or neutral-white collared button-up shirts, fitted but not tight, tucked into charcoal, dark-gray or black high-waisted short pencil skirts. Some sleeves are rolled to the forearms, collars open naturally by one or two buttons, and the shirts remain fully opaque with realistic folds around the shoulders, elbows and waist. Every leg is fully covered by thin smoke-black sheer tights. Believable knee, thigh and calf contours remain visible beneath the hosiery, but the legs must never become bare, thigh-high stockings or over-the-knee socks. Add pointed patent-leather stiletto pumps, mostly glossy black, with two or three vivid red patent heels or red soles creating a restrained red-and-black visual rhythm across the lower frame. The five seated women form the dominant foreground with crossed, parallel or diagonally extended legs. The central woman sits most upright with her hands resting naturally together near her lap. A woman with airy straight bangs rests one cheek on her hand. A long-haired woman on the right lightly supports her chin. The far-right subject leans inward with one or both hands close to her chin. The back-left woman has long deep-chestnut waves and raises one hand toward her hair. Preserve uneven seat heights, slightly offset shoulder lines, natural body occlusion, overlapping legs and partial cropping of the edge subjects. Every arm, hand, finger, knee, leg and shoe must remain clearly connected and anatomically plausible. Hair colors include natural black, black-brown and deep chestnut. Use varied hairstyles such as side-parted waves, long center-parted straight hair, shoulder-length straight hair, neat airy bangs, long middle-parted S-waves and a loose half-up hairstyle with face-framing strands. Hair should feel smooth yet weighted, with visible part lines, fine flyaways and slightly separated ends. Avoid identical plastic gloss. Makeup follows contemporary East Asian urban-office and soft Korean beauty styling: lightweight semi-matte foundation, gently straight brows, thin brown-black eyeliner, clean separated lashes, muted peach or rose blush, and coral, dusty-rose or soft-pink lips. Avoid oversized eyes, heavy contouring and dramatic glam makeup. Clearly visible skin is limited to faces, ears, necks, small areas of collarbone and upper chest inside the shirt collars, wrists, forearms and hands. Chests, waists, hips, buttocks and legs remain covered by clothing or tights. Use naturally varied fair-to-light warm skin tones with neutral, peach or faint rosy undertones. The skin should appear and feel soft, fine-grained, clean and semi-matte, like lightly moisturized skin beneath a thin foundation layer. Retain faint pores, subtle under-eye texture and hand-joint detail rather than waxy or plastic skin. Place the camera near floor or lower-shin height and tilt it upward by approximately 5 to 10 degrees from directly in front. Use a close shooting distance and a 20 to 26 mm full-frame equivalent wide-angle lens, making the foreground legs and shoes visibly larger than the upper bodies while avoiding fisheye distortion or severe stretching at the edges. The image should resemble a rear-smartphone-camera group photo with mild computational HDR and restrained beauty processing, or a full-frame wide-angle photograph with similar rendering. Keep the image clean and sharp while retaining extremely fine sensor grain, uneven highlights, fabric creases and small human imperfections. Use moderately deep focus so all seven faces, the tights-covered legs and the foreground shoes remain substantially sharp, with focus biased slightly toward the central woman and no heavy background blur. Set the scene in a bright, orderly modern office lounge or meeting area. Include a white suspended ceiling with several circular recessed downlights, pale cabinetry or office partitions on the left, a bright window or glass opening on the right, light-beige chairs, and a polished dark floor with pale abstract stone or marble-like patterns. Broad white ceiling illumination combines with slightly cooler daylight entering from the right, producing a mixed color temperature around 4300 to 5000K. Create gentle physical highlights on foreheads, noses, cheeks and forearms, with shallow gray shadows beneath jaws and around eye sockets. Sheer tights and patent shoes should carry controlled linear and point-like reflections without clipping, while soft shadows and blurred reflections appear under the chairs and across the polished floor. The scene should feel like seven familiar coworkers who had just gathered for an impromptu office portrait. The shutter has already been pressed, yet they are still holding their chin-resting gestures, crossed legs and subtle inward leans. In the next moment, their hands may lower and the overlapping legs may shift. Keep the atmosphere bright, friendly, quietly confident and moderately polished, while preserving the accidental irregularity and emotional residue of a real human photograph.



















