InkRoom
InkRoom
Public prompt创意海报

YouTube 缩略图 - Tiny Man vs Giant Ant Scoreboard Scene

✓Original text is publicUpdated:
GPT 8.4/10
YouTube 缩略图 - Tiny Man vs Giant Ant Scoreboard ScenePrompt preview
Results depend on the model, inputs and generation settings.

Full prompt

Original author text

This public page preserves the author's original prompt. Review the preview and any published evaluation, then copy the text or open it as a draft. Choose the model, references and current cost in the creation workspace before generating.

Create a cinematic vertical 3D cartoon scene on a realistic forest floor, framed like a mobile video still. In the center foreground, show one cute miniature bearded man, {argument name="character name" default="Montaser"}, with an oversized caricature head and worried expression, standing stiffly with arms slightly out while trapped in a large white spider web behind him. He has short dark brown hair, a trimmed beard, raised sad eyebrows, and big anxious eyes. Dress him in exactly four main outfit pieces: a dark denim jacket, a gray T-shirt, black pants, and white sneakers. To his right, show one giant glossy black cartoon ant with large expressive eyes, two antennae, six thin legs, and bent forearms, leaning toward him with a curious intimidating look. Behind them, the spider web radiates clearly across green leaves and stems. At the top center, add a game-style scoreboard overlay: a dark rounded rectangle with exactly two circular avatar icons, the left icon showing the man on a blue background, the right icon showing the ant on an orange background, and large white score text {argument name="score text" default="2 - 1"} between them. The environment is a macro-scale forest floor with dirt, small pebbles, tiny plants, blurred green foliage, warm daylight, shallow depth of field, and cinematic bokeh. Use polished Pixar-like 3D rendering, soft realistic lighting, detailed textures, playful comedy tension, and a vertical 9:16 composition. Add a small white stylized logo watermark at the bottom right reading {argument name="watermark text" default="MONTASER"}.

Adjust the model, settings and references before generating.

Use prompt →

Prefill first, then confirm generation and the current cost.

GPT evaluation

Overall score
8.4 / 10

GPT-6-luna

AI evaluation for creative reference

Model: GPT-6-luna Overall score: 8.4 / 10 Prompt quality: 8.2 / 10 Image quality: 8.7 / 10 Prompt–image alignment: 8.4 / 10 画面完成度高、主体与记分牌一眼可辨,整体符合提示词;上线前建议让蛛网更明确地缠住人物,并避免蚂蚁贴近画面边缘。

Prompt quality8.2 / 108.2
Image quality8.7 / 108.7
Prompt–image alignment8.4 / 108.4

Community reviews

No creator reviews yet.

View and review →