① Always switch the mode to 'Thought' or 'Pro' (I feel 'Thought' is better) ② 'Describe the scene in sentences' rather than listing keywords ③ Specify the subject, background, and atmosphere as a set of three points ④ Don't aim for perfection in one go; apply 'gradual corrections' ⑤ Avoid negative expressions; give instructions in positive sentences ⑥ Add quality keywords (4K, high resolution) in English ⑦ Clearly state the purpose at the beginning (e.g., "Diagram for a proposal") ⑧ Exclude unnecessary elements using negative prompts ⑨ Do not attempt complex edits all at once; proceed in segments ⑩ Save frequently used prompts as templates

A lost kitten sheltering from the rain under the eaves of an old wooden house. The kitten is small, gray, and visibly wet, with fur clinging to its body. The background features a close-up of the aged wood of the house structure, covered in

"A soft beauty still life inside a miniature world handcrafted entirely from yarn, wool, and plush textiles. Two knitted night cream jars float gently above a pastel pink felt backdrop. The hero jar is fully sculpted from thick knitted sti

Top-tier Chinese-style fantasy anime CG, cinematic oriental fantasy blockbuster texture, ultra-high saturation, golden ink blending, surreal visual spectacle, magnificent and shocking, strong sacred oppressive aura. 16:9, 15 seconds, smooth

Illustrate [SUBJECT] using a combination of thin lines and large flat shapes. Keep the interaction sparse and intentional. The result should feel contemporary and design-forward.

{ "subject_and_pose": { "description": "A photorealistic, highly detailed image of a beautiful Sydney Sweeney with shoulder-length platinum hair featuring soft bangs. She has fair skinned tone with a noticeable glossy, wet sheen, suggesting

{ "type": "photograph", "aesthetic": { "mood": "romantic and elegant", "style": "cinematic fine-art photography", "color_contrast": "vibrant red dress contrasted against earthy natural tones" }, "subject": { "description": "Woman resembling

{ "objective": "Create a side-by-side visual comparison of Hagia Sophia, featuring a technical architectural sketch and a real-life photograph", "image_specifications": { "style": "Mixed media (Architectural drawing + Real photography)", "l

Create a hyper-realistic, high-detail studio photoshoot featuring the same person from the reference photo with the exact facial features, skin tone, hairstyle, proportions, and identity fully preserved (no changes to face or structure). He

在「东京塔」的位置,根据当地当前时间氛围和实时天气制作图片。请让指定的角色在该地点游览,使其融入场景。 生成画面: 生成一张画面为竖版3:4比例,单张图固定九宫格布局,三行三列,每个格子为独立镜头。 相机与视角: – 使用超广角或鱼眼感的镜头(大约等效全画幅 12–18mm 的观感) – 相机角度必须与原图有显著变化,可以使用的夸张机位包括: • 从正下方向上看的仰视视角 • 从正上方向下看的俯视视角 • 贴近地面的超低机位 • 从上往下的高机位 • 倾斜的「荷兰角度