Generor 登录注册

生成器公开

像素艺术通过位深和调色板控制，生成复古与现代风格的像素艺术

像素艺术描述 *

提示：先选择时代（8位为复古风，现代为独立风），然后搭配调色板。Game Boy + 角色可制作出色的粗犷头像；PICO-8 + 场景营造多彩的独立氛围。

像素艺术风格

选择位深时代——8位是粗犷复古风，现代是精细的独立像素艺术。点击?查看预览。

8-bit Retro

Classic NES / GameBoy era pixel art. Limited palette, blocky pixels, no anti-aliasing. Iconic retro charm.

16-bit

SNES / Genesis era pixel art with richer colors, subtle dithering, and more detailed sprites.

32-bit

PlayStation 1 era detailed pixel art with smooth shading, semi-transparency, and rich palettes.

Modern Pixel

Contemporary pixel art with high detail, cinematic lighting, soft dithering — Hyper Light Drifter / Stardew vibes.

Isometric Pixel

2.5D isometric pixel art for strategy, builder, and dungeon-crawl aesthetics.

Hand-drawn Pixel

Painterly pixel art with visible brush-style pixel placement — artisanal, indie-game feel.

调色板

选择经典复古主机调色板、现代预设，或让 AI 自动挑选。点击 ? 查看预览。

AI Choose

Let the AI select the most fitting palette for the subject and era.

Game Boy Green

Classic 4-shade DMG green palette: deepest swamp green to bright lime. Iconic 1989 monochrome.

NES (1985)

Original Nintendo 54-color palette. Bold, slightly muted primaries — the look of Mario, Zelda, Metroid.

Commodore 64

16-color C64 palette. Earthy warm tones and dusty saturated hues — true 8-bit home computer feel.

Game Gear

SEGA Game Gear palette — vivid 12-bit colors with that handheld 1991 LCD warmth.

PICO-8

Modern 16-color fantasy console palette. Hot pink, peach, navy, lime — favorite of indie pixel artists.

CGA (DOS)

4-color CGA palette: black, cyan, magenta, white. Brutally limited classic PC vibe.

Modern Vibrant

Bright saturated colors with extended range. Mobile-game and modern indie pixel-art aesthetic.

Monochrome

Single hue with shades. Stylish and distinctive — works great for moody, atmospheric scenes.

Pastel

Soft, light, candy-colored palette. Cozy, kawaii, low-stress aesthetic.

Dark Fantasy

Deep, moody palette — purples, blacks, blood reds, cold blues. Roguelike / horror pixel-art feel.

主体类型

您要生成哪种像素艺术？点击 ? 查看预览。

Character

Heroes, NPCs, creatures, mascots — single subject pixel character art.

Scene / Landscape

Pixel landscape, environment, or cinematic scene with depth and atmosphere.

Item / Icon

Single small object: sword, potion, key, food. Crisp and readable.

Tileset / Pattern

Tileable terrain, walls, or repeating pattern that connects seamlessly.

Portrait

Pixel-art bust portrait — RPG dialogue style, with detailed face and shoulders.

UI / HUD

Pixel UI element: button, panel, health bar, menu frame.

AI 模型

P-Image 1 FREE

Pruna P-Image (direct) — sub-second text-to-image built for production. Strong prompt adherence and crisp text rendering at standard aspect ratios. 阅读更多 →

Z-Image Turbo 1

Login required to use this model. Alibaba Z-Image Turbo — lightweight text-to-image with bilingual (Chinese+English) text rendering. Fast, cheap, flexible resolutions from 512×512 up to 2048×2048. 阅读更多 →

Flux Schnell 2 FREE

Ultra-fast image generation at a fraction of the cost. Perfect for quick iterations and testing ideas. 阅读更多 →

P-Image Edit 2 FREE

Pruna P-Image Edit — focused image editing with 1-5 reference images, sub-second inference, and exact-prompt adherence. Strict image-to-image (requires at least one source image). 256-1440 px output in standard aspect ratios. 阅读更多 →

Wan 2.6 Image 2

Login required to use this model. Alibaba Wan 2.6 text-to-image — strong cinematic photography and artistic styles. Renders at 1280×1280 to 1440×1440 with five aspect ratios. 阅读更多 →

Grok Imagine 4

Login required to use this model. xAI's Imagine API image model — fast generation and editing with strong prompt fidelity. 阅读更多 →

Qwen Image 4

Login required to use this model. Alibaba Qwen Image — flagship text-to-image with strong text rendering, multilingual prompt support, and crisp realism. 阅读更多 →

Wan 2.7 Image 4

Login required to use this model. Alibaba Wan 2.7 image — text-to-image, image editing with up to 9 reference images, and multi-image reference generation. Up to 2K resolution. Was previously via Replicate at ~30× the cost. 阅读更多 →

SeedEdit 3.0 6

Login required to use this model. BytePlus SeedEdit 3.0 — focused image-editing model. Takes a source image plus an instruction and applies the edit in-place ("make the bubbles heart-shaped", "change the sky to sunset"). Adaptive output sizing follows the input image dimensions. Strict image-to-image only (no pure text-to-image). 阅读更多 →

Seedream 4.0 6

Login required to use this model. BytePlus Seedream 4.0 — multimodal image creation with text + single-image + multi-image inputs. Multi-image blending up to 10 references, sequential image-set generation up to 15 outputs, 4K ultra-HD support. Direct via BytePlus. 阅读更多 →

Seedream 5.0 Lite 7

Login required to use this model. BytePlus Dola-Seedream 5.0 Lite — flagship image model with web-connected retrieval, multi-image fusion, image-set generation, and strong consistency preservation. Supports text-to-image and image-to-image (with up to 4 reference images). Up to 2K output. Direct via BytePlus. 阅读更多 →

Qwen Image Edit 8

Login required to use this model. Alibaba Qwen Image Edit — image-to-image with multi-reference editing, text-in-image rendering, and example-based composition. 阅读更多 →

Seedream 4.5 8

Login required to use this model. BytePlus Seedream 4.5 — refined image model with strong editing consistency, multi-image fusion, finer detail control, natural small-text and face rendering, and 2560×1440 to 4096×4096 output. Supports text-to-image and image-to-image with up to 4 reference images. 阅读更多 →

Wan 2.7 Image Pro 8

Login required to use this model. Alibaba Wan 2.7 image Pro — premium variant with 4K text-to-image, thinking mode for higher quality, image editing, and multi-image reference. 阅读更多 →

Seedream 4.0 9

Login required to use this model. Next-generation image model with unified generation & editing. Supports sequential image generation for coherence and multi-reference workflows. 阅读更多 →

Grok Imagine Quality 10

Login required to use this model. xAI's higher-quality Imagine image model — sharper detail and stronger composition than the standard Grok Imagine, at a higher per-image cost. 阅读更多 →

Gemini 2.5 Flash Image 12

Login required to use this model. Google's fast image model with good quality and speed. Excellent at following natural language prompts. ⚠️ This model only supports Square (1:1) and Match Input aspect ratios. 阅读更多 →

Seedream 4.5 12

Login required to use this model. Upgraded Bytedance image model with stronger spatial understanding and world knowledge. 阅读更多 →

Nano Banana 2 14

Login required to use this model. Google's latest fast image model with high-efficiency production-scale visual creation. Supports multiple resolutions up to 4K. 阅读更多 →

Nano Banana Pro 27

Login required to use this model. Google's professional design engine with a reasoning core for studio-quality 4K visuals, complex layouts, and precise text rendering. 阅读更多 →

管理 Image 模型

宽高比

unspecified Unspecified

match_input_image Match Input

1:1 Square

3:4 Vertical

4:3 Horizontal

16:9 Wide

9:16 Tall

图片数量

一次生成多个，享受最高 10% 的批量折扣。

1 image 9 FREE

2 images 18 FREE

3 images 27 FREE

4 images 2.78% off 35 FREE

5 images 4.44% off 43 FREE

6 images 5.56% off 51 FREE

7 images 6.35% off 59 FREE

8 images 6.94% off 67 FREE

9 images 8.64% off 74 FREE

10 images 10% off 81 FREE

下载格式

推荐使用 PNG——JPEG 压缩会破坏清晰的像素边缘。

PNG

JPEG

WebP

隐私模式

公开

您的作品将对所有人可见，并可能出现在公开图库和搜索结果中。

私密

只有您能看到此作品。它不会出现在任何公开信息流中，其他人也无法访问。

团队

仅与您的团队成员分享此创作。团队以外的其他人无法访问。

许可证

Generor Open

所有人均可免费使用、修改和商用，无需署名。了解更多 →

Generor Exclusive

只有您能使用此作品。其他人不能复制、修改或分发它。了解更多 →

输出语言

自动（输入语言）

English (United States)

Spanish (Spain)

French (France)

German (Germany)

Italian (Italy)

Portuguese (Brazil)

Arabic (Generic)

Bengali (India)

Bulgarian (Bulgaria)

Croatian (Croatia)

Czech (Czech Republic)

Danish (Denmark)

Dutch (Belgium)

Dutch (Netherlands)

Estonian (Estonia)

Finnish (Finland)

Greek (Greece)

Gujarati (India)

Hebrew (Israel)

Hindi (India)

Hungarian (Hungary)

Indonesian (Indonesia)

Japanese (Japan)

Kannada (India)

Korean (South Korea)

Latvian (Latvia)

Lithuanian (Lithuania)

Malayalam (India)

Mandarin Chinese (China)

Marathi (India)

Norwegian Bokmål (Norway)

Polish (Poland)

Romanian (Romania)

Russian (Russia)

Serbian (Cyrillic)

Slovak (Slovakia)

Slovenian (Slovenia)

Swahili (Kenya)

Swedish (Sweden)

Tamil (India)

Telugu (India)

Thai (Thailand)

Turkish (Turkey)

Ukrainian (Ukraine)

Urdu (India)

Vietnamese (Vietnam)

温度 ?

1.0

控制 LLM 模型的创意性与一致性。默认值：1.0。越低 = 越聚焦/确定，越高 = 越有创意/随机。

思考中

推理模型在回答前会先思考。关闭 = 1×，开启 = 2×，高 = 模型每次调用基础费用的 3×。

关闭 1 FREE

开启 2 FREE

高 3 FREE

免费 AI 像素艺术生成器

生成专门的像素艺术图像，可精细控制位深时代（8 位、16 位、32 位、现代）、标志性主机调色板（Game Boy、NES、C64、PICO-8 等）以及主体类型（角色、场景、道具、瓦片集、肖像、UI）。非常适合独立游戏开发者、复古艺术爱好者，以及任何追求清晰、怀旧像素美学的人。

适合谁

制作 2D 像素游戏的独立游戏开发者、创作同人作品的复古游戏爱好者、需要快速素材的业余 game jam 参与者、想要厚重 8-bit 头像的社媒用户、设计像素风频道美术的主播，以及探索正统受限调色板像素艺术极限的数字艺术家。

核心功能

从正统 8-bit 复古到现代独立像素艺术的六种位深预设，十一种调色板选项，包括忠实还原的 Game Boy DMG 绿、NES、Commodore 64、Game Gear、PICO-8 和 CGA，六种主体类型构图（角色、场景、道具、瓦片集、肖像、UI），宽高比控制，PNG 默认下载以保留清晰像素，以及一次生成多个变体时最高 10% 的批量折扣。