CHARACTER: Canvas 1024x1024 PNG, transparent background.

Style: clean bold cartoon, thick black outline (about 8px), flat colours, one soft shadow tone, small glossy highlights, warm playful palette.

Draw ONE base: a cool cartoon cat-headed person, facing straight at the viewer, head centred on x=512, both eyes level and looking at the viewer.

Head: round cat head, 350px wide at the cheeks (x=337 to x=687). Small rounded ears close to the head, ear tips at y=210, roughly over x=380 and x=644; skull dome top about y=245 between the ears; chin y=665.

Eyes: big expressive green eyes with glossy highlights, centres at y=425, about x=440 and x=584. Tiny pink nose at about y=505 on x=512. Simple neutral closed mouth, relaxed and confident, centred at about y=560.

Short ginger fur with white cheeks and muzzle. Short neck, narrowest at y=700 (about x=432 to x=592), meeting rounded shoulders at y=740 (neck base about x=422 to x=602). Bare ginger-furred shoulders and upper chest running off the bottom edge; arms down and out of view; nothing in front of the chest.

Do NOT draw any clothing, collar, scarf, hat, glasses, chain or held item.

Output: character_base.png (exactly one file).

Weights file: character_weights.json with {"character_base":100}.

BACKGROUND: Canvas 1024x1024 PNG, fully opaque, no character, no scene, no texture, no outlines. Flat warm playful tones to match a bold cartoon cat. Ten flat solid fills, two tones of each colour: sky blue (#8ECDF2, #6FB8E8), mint (#A8E6CF, #8DD9BC), lavender (#C9B6E8, #B49DDE), peach (#FFC9A8, #FFB48C), butter yellow (#FFE79A, #FFDC73).

Plus two soft top-to-bottom gradients as the rare ones: peach to lavender, and sky blue to mint.

Outputs: background_sky_blue_01.png, background_sky_blue_02.png, background_mint_01.png, background_mint_02.png, background_lavender_01.png, background_lavender_02.png, background_peach_01.png, background_peach_02.png, background_butter_01.png, background_butter_02.png, background_gradient_peach_lavender.png, background_gradient_sky_mint.png.

Weights file: background_weights.json, each solid 9, each gradient 5 (total 100). Also write artifacts/base_b.png and artifacts/base_c.png: two more takes of the SAME character on the SAME template and pose, each a SEPARATE, FRESHLY GENERATED image (run the image tool again for each one; never copy, edit, recolour or re-save base.png), so that if one comes out too big, too small or off-centre another may fit.

Write artifacts/base.png, artifacts/background_01.png .. background_12.png, and artifacts/traits.json: {"backgrounds":[{"file","name","weight"}...]} with weights summing to 100.