① Create a "Polar Bear" and a "Panda" wearing ice skates, along with the background location. Normal chat-based input is also acceptable. Whether you generate them all at once or separately, the process is the same. ② Perform annotation on the image. This is the most troublesome part, so I made it a tool. Based on the file name, I create a prompt that organizes "which part of which image to reference." (Pose / Background / Face / Clothing, etc.) ③ Add supplementary information such as composition and color scheme for the final generation.

{ "subject": { "identity": "Reference-based female", "description": "A confident woman in snowy alpine mountains, carrying a snowboard resting diagonally on her shoulder. Face and hair color should match the reference image, with all other

{ "generation_request": { "meta_data": { "task_type": "luxury_editorial_beauty_macro_series", "language": "en", "priority": "highest", "style_version": "v1.0_CHOCOLATE_GLOSS_COUTURE" }, "input": { "mode": "image_to_image", "reference_image_

Preserve the face, proportions, and external features of the model as in the reference. A minimalist monochrome fashion editorial triptych featuring three stacked cinematic frames. The subject is a young man with short dark hair and wearing

Ultra-realistic 8K cinematic photograph of the subject, hyper-detailed skin texture, natural facial imperfections, sharp focus, professional studio lighting with soft shadows, realistic depth of field, HDR, global illumination, photorealist

"Create a whimsical, playful illustration featuring [CHARACTER / SUBJECT] as the central focus. The character is drawn with simplified features, a small rounded head, and minimal facial detail, wearing [HEADWEAR / CLOTHING DESCRIPTION]. The

Cyberpunk Palace of Versailles Marie Antoinette's bedroom

{ "meta": { "aspect_ratio": "3:4", "quality": "ultra_photorealistic, raw, unedited photograph", "resolution": "8k", "camera": "Mirrorless camera (e.g., Canon EOS R5)", "lens": "50mm f/1.2 portrait lens", "style": "Soft natural light portrai

[ INPUT IMAGE: USER_PHOTO ] Use the person in the input image as the ONLY subject. Preserve their identity and facial features clearly. Create a hyper-realistic high-fashion editorial photo inside a surreal 3D geometric “color box” room (

A hyper-realistic cinematic fashion photograph of a stunning young woman in her early 20s, full body visible, standing in a modern city center during golden hour. She leans casually with one shoulder against a traffic light pole, unaware of