IMAGE EDITING TASK — GPT Image 2 (image-to-image with a reference). Base image = IMAGE 1 "ПЕРСОНА" (cybernetic man in a dark checked three-piece suit sitting at a desk; matte-black segmented helmet-mask with glowing blue eyes and a small mouth-line; framed "eye / СБП / МИР / под наблюдением" poster and rainy Kremlin window behind him). Reference = IMAGE 2 "перс редакт 5" — copy ONLY TWO things from it onto IMAGE 1. Everything else in IMAGE 1 stays 100% identical. Copy from IMAGE 2 — ONLY these two things: 1. HELMET LINES: copy the blue glowing edge-lines / panel seams running across the helmet in IMAGE 2 (the sleek grooved panel lines over the forehead, temples, brow and cheeks) and apply the exact same line layout, thin blue glowing style and placement onto IMAGE 1's mask. 2. MOUTH SHAPE: copy the exact MOUTH SHAPE from IMAGE 2 onto IMAGE 1 — same form, size and position of the lower-face mouth. HARD CONSTRAINTS — do NOT change anything else: Keep IMAGE 1's overall mask shape, proportions, nose, eyes and blue eye-glow exactly as they are. Do NOT change the suit, tie, pocket square, gloves, pose, hands, desk and all objects (whisky glass, notebook, pen, lamp, books), the framed poster, the window, rain, Kremlin tower or the background. The ONLY allowed modifications are: (1) adding IMAGE 2's blue helmet lines and (2) applying IMAGE 2's mouth shape. Nothing else. STYLE: photorealistic, cinematic, dark moody lighting — identical to IMAGE 1.
Free to start · Generate videos and images with AI in seconds