聊天GPT
湯姆和傑瑞最好的朋友肖像
為聊天GPT 編寫。不同型號的結果和參考照片支援可能有所不同。
使用提示詞前
列出的工具:聊天GPT。完整說明:2,385 個字元。 1 個提供的範例影像。
This prompt mentions reference images. Read its instructions for the required number of photos and identity constraints. We have not independently tested this prompt. Tool labels and supplied images are not a guarantee of compatibility or output quality.
完整提示詞
Use the uploaded image as the PRIMARY VISUAL REFERENCE. Preserve the exact recognizable facial identity, facial structure, hairstyle, skin tone, natural age and realistic body proportions of the human subject.
Recreate the same warm, playful composition with the subject standing naturally beside Tom, with Tom gently leaning close and posing like a playful best friend. Preserve the subject’s black graphic sweatshirt featuring Tom and Jerry artwork, relaxed-fit blue jeans and white sneakers. Keep the casual standing pose with one leg slightly crossed and the body naturally leaning toward Tom.
Recreate Tom as a realistic, physically present full-sized character mascot/costume, maintaining his recognisable grey fur, white muzzle and belly, large expressive ears, long tail and characteristic proportions. The character should have believable soft fur, subtle texture variation, realistic fabric/foam construction and natural contact shadows, while retaining the familiar animated appearance.
Keep the cosy hand-drawn bedroom/studio-style backdrop with a muted blue-green wall covered in playful doodles, hearts, stars and handwritten friendship-style drawings. Preserve the intimate, youthful scrapbook aesthetic while making the entire scene look like a real photographed setup.
Use soft indoor lighting, realistic skin texture, individual hair strands, authentic clothing folds and natural shadows. The human subject MUST look directly into the camera with a relaxed, natural expression. Tom should face naturally toward the camera with a friendly playful expression.
The final result should look like a real photograph of a person posing with a professionally made Tom character costume in a decorated room, not a CGI render or AI illustration. Natural DSLR photography, realistic lens depth, subtle photographic grain, authentic textures and believable lighting, 1122 × 1402 px, vertical.
Negative Prompt
AI-generated appearance, CGI, 3D render, digital illustration, plastic fur, synthetic costume, flat cartoon character, wrong identity, pasted face, altered hairstyle, face distortion, bad anatomy, distorted hands, extra fingers, warped body, unrealistic Tom proportions, floating limbs, mismatched lighting, artificial shadows, fake wall texture, excessive saturation, excessive HDR, oversharpening, plastic skin, blur, watermark, random text, logo, AI artifacts.複製完整的提示並根據要求使用您自己的參考照片。
此提示提供的範例影像。此提示尚未經過我們網站的測試。


