Create a photorealistic miniature diorama poster based on the uploaded reference images.

REFERENCE ROLES

Input Image 1 = SUBJECT / SOURCE PHOTO. Use this image as the primary source for the scene, architecture, composition, objects, proportions, and overall visual identity. Input Image 2 [https://www.instagram.com/p/C-CaDwESzHK/?img_index=1] = MINIATURE DIORAMA / SCALE REFERENCE. Use this image only as a reference for the miniature-model aesthetic, handcrafted physical materials, tilt-shift photography, depth of field, and the visual relationship between a human hand and a small diorama. Do not copy the exact composition or objects from Input Image 2.

RESULT

Transform the real-world scene in Input Image 1 into a highly realistic handcrafted miniature architectural diorama, photographed as a physical scale model. The result should look like a professionally photographed miniature model rather than a digitally generated scene.

SCENE

Reconstruct the recognizable scene from Input Image 1 as a miniature diorama:

preserve the original buildings and their recognizable shapes preserve the arrangement and relative positions of the storefronts, roofs, road, hillside, utility elements, crates, bicycles, signs, doors, windows, and other characteristic objects retain the overall perspective and visual hierarchy of the source photograph retain the original atmosphere and color character of the location while translating everything into miniature scale preserve distinctive imperfections, weathering, stains, aged surfaces, corrugated metal, rough concrete, brick, wood, asphalt, and other visible materials

MINIATURE CONSTRUCTION

Everything in the scene must visibly exist as a physical miniature model:

tiny architectural structures hand-built walls and roofs miniature corrugated metal sheets tiny wooden doors and window frames miniature bricks and rough concrete tiny utility poles and overhead wires miniature crates, bicycles, signs, vehicles, and roadside objects subtle handmade imperfections and slightly irregular construction realistic material thickness and believable miniature construction details

Materials should have convincing physical scale. Surfaces should not look like flat textures pasted onto a 3D render. Include tiny seams, edges, joints, scratches, weathering, dust, paint variation, and small handmade irregularities.

HUMAN HAND / SCALE RELATIONSHIP

Add a real human hand in the extreme foreground, partially entering the frame and interacting naturally with the miniature diorama.

The hand must clearly establish the scale relationship:

the hand is much closer to the camera than the diorama natural adult human hand proportions realistic skin texture, fingernails, subtle wrinkles, and soft imperfections the hand should gently hold, support, pinch, or stabilize one edge of the miniature model the interaction must look physically plausible the hand should not obscure the important architecture the hand must immediately communicate that the entire scene is a small physical model

Use realistic depth and perspective so that the hand, miniature buildings, and distant background clearly occupy different spatial planes.

TILT-SHIFT PHOTOGRAPHY

Photograph the miniature as if captured with a professional tilt-shift macro photography setup.

Use:

pronounced but natural miniature-style depth of field a sharp focal plane across the most important central portion of the diorama gradual optical blur toward the foreground and background realistic lens compression and perspective subtle macro-photography characteristics physically believable focus falloff crisp miniature details inside the focal plane soft optical bokeh outside the focal plane

The tilt-shift effect should enhance the impression of a real miniature model, not become an exaggerated artificial blur filter.

LIGHTING

Use realistic photographic lighting appropriate for a premium miniature-diorama poster:

soft natural directional light gentle highlights on metal, glass, painted surfaces, and skin subtle contact shadows between miniature objects realistic ambient occlusion soft shadows beneath buildings and objects natural tonal variation no excessive HDR no blown-out highlights no artificial plastic-looking illumination

CAMERA / COMPOSITION

Create a polished vertical poster composition, approximately 4:5 aspect ratio.

Use a low-to-medium camera angle that makes the miniature environment feel spatial and immersive while maintaining the recognizable composition of Input Image 1.

The miniature hand should occupy the foreground edge of the composition and act as an immediate scale cue. Keep the central architectural elements clearly visible.

The final image should feel like a carefully photographed collectible architectural diorama displayed as a premium creative poster.

VISUAL QUALITY

Photorealistic, physically believable miniature photography, highly detailed macro photography, realistic handcrafted materials, realistic skin, realistic optical depth of field, subtle filmic tonal response, fine surface texture, convincing scale cues, natural imperfections.

The image should feel tactile and photographable: the viewer should believe that they could physically pick up the miniature and inspect it.

PRESERVE

Preserve the recognizable appearance and visual identity of Input Image 1:

building shapes architectural arrangement major objects road geometry roof structures storefront details characteristic colors distinctive signs and visual details overall atmosphere

Do not replace the scene with a generic miniature village.

CHANGE ONLY

Convert the real-world scene into a physical miniature diorama and add the foreground human hand and miniature-photography treatment.

Do not change the fundamental identity or layout of the source scene.

NEGATIVE CONSTRAINTS

No generic fantasy village.

No redesigned architecture.

No futuristic elements.

No cartoon appearance.

No toy-like plastic buildings.

No 3D-rendered CGI appearance.

No smooth game-engine assets.

No excessive tilt-shift blur.

No giant hand.

No distorted fingers.

No malformed hands.

No duplicated objects.

No floating objects.

No impossible geometry.

No inconsistent scale.

No extra buildings that were not present in the source.

No unnecessary people.

No random text.

No extra logos.

No watermark.

No artificial UI elements.

The final result should look like a real professional photograph of a meticulously handcrafted miniature version of Input Image 1, with the foreground human hand providing an unmistakable physical scale reference. 【The input image 1 is the main photo.】