单 ref portrait → spaghetti pieces 拼出轮廓 · 跨 medium 物理材质 · sparse gap-heavy · pack avatar-redraw-2026q2 variant
项目内首验证 2026-05-01 · 57s wall · pack avatar-redraw-2026q2 variant 6/7. genuine pasta 形状 · pale yellow · uneven / bent / 不齐放置 · 大量空白 · 真"用面条拼脸"感. 跟 torn-paper 同 medium-transform 家族 · 但 pasta 是 sparse outline (vs paper 是 fill). Production: 餐饮 / 面食品牌 / 面条节 marketing / 食物纪录片 visual.
date: '2026-05-01T14:32:14+08:00'
result: pass
prompt:
text: >-
Transform the reference image into a sparse pasta-line flat lay. Rebuild the scene using only a
small number of cooked spaghetti pieces arranged as rough outlines on a plain white background.
Use the pasta to suggest the main face, body, clothing, and surrounding objects with simple
broken contours. Keep many gaps and empty spaces. The pasta pieces should be pale yellow,
slightly glossy, uneven, bent, and imperfectly placed. The final image should look handmade,
minimal, awkward, and funny — like a failed but recognizable copy of the original photo made
from noodles. Do not make it dense, decorative, elegant, or polished. No ink lines, no pencil
lines, no realistic rendering, only pasta pieces.
refs:
- source: yuan.studio/public/images/yuan_kid_history/raw_frame_001.png
sha256: null
error: file not found at write time
upload_url: >-
https://personalized-video-refs.tos-cn-beijing.volces.com/4a21e4ba8a91/raw_frame_001.png?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYjM3ZTcxNjI5ZjFkNGZmYjgyMTNjNWRjZjU4N2IzNjY%2F20260430%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20260430T175741Z&X-Tos-Expires=86400&X-Tos-SignedHeaders=host&X-Tos-Signature=e00dec5d3246089dde91813f6c7914ef6c2b1d22eaca22aff4207093249a22d0
provider:
id: gpt_image_2
relay: apimart
config:
aspect_ratio: '1:1'
size: '1:1'
'n': 1
output:
path: ./redraw_pasta_v1.png
bytes: 1787774
wall_seconds: 57.2
task_id: task_01KQH3R3TZWH0SWA3D2H8AD9J0
script: experiments/avatar_redraw_pack/_runner.py
cost_yuan: 0.5
notes: Pasta line flat lay · 物理材质 (spaghetti) · 跨 medium · pack avatar-redraw-2026q2 variant 6/7
recipes/image_gen/gpt_image_2/prompts/.