# Monkey raising a lantern Six distinct generated poses show the monkey raising and lowering the lantern and blinking Web page: Other languages: [简体中文](https://promptseen.dev/zh-hans/prompts/image26-g01-monkey-raising-a-lantern/index.md) ![Six distinct generated poses show the monkey raising and lowering the lantern and blinking.](https://promptseen.dev/media/a_382/image26-g01-monkey-raising-a-lantern-detail-a3b0c412c6e7.webp) Use the independently generated monkey reference. ## Test record - Tested with GPT Image 2.6 - 512 × 512 · 1:1 - Tested 2026-11-04 - Reference image required - Updated 2026-11-04 ## Prompt · Simplified Chinese ```text 制作一张供后期裁帧合成 GIF 的动画精灵图，PNG 静态画布，宽 1536 高 1024 像素，精确三列两行，共六个等大的 512×512 正方形帧。每格是独立完整画面，按从左到右、从上到下依次播放。无外边距、无格线、无分隔条、无编号。角色不要跨越格子边界。所有格子中角色尺寸、脚下基线、镜头、背景与光照必须固定一致，只有动作姿态逐步变化。请把以下动画描述转成六个清晰不同的连续姿态；最后一格回到第一格姿态，以便循环。本次交付的是完整六格精灵图，不要只画一个姿势。使用输入小猴子图片保持角色、衣服、灯笼和环境一致。 动作与主题： 生成一段正方形无缝循环 GIF：一只穿绿色冬装的小猴子站在雪林里，身后远处有亮着暖灯的小木屋。它双手托着纸灯笼，缓慢举到脸旁，眨眼看向灯光，再把灯笼放回胸前。身体位置和镜头固定，灯笼始终握在手中，最后一帧回到起始姿势。动作简洁清晰，避免大幅飘雪和镜头移动。 ``` ## How to use Use the exact recorded prompt and the displayed original reference assets in order. Changes to the prompt or inputs create an untested variant. ## Observed result Six distinct generated poses show the monkey raising and lowering the lantern and blinking. Cropped row-major into a 512px GIF, 300ms per frame, infinite loop; slight background drift between poses. This is a composed GIF, not native GIF output. ## GIF assembly The model generated a 3-column by 2-row PNG sprite sheet. Crop equal cells in row-major order and encode six frames at 300 ms per frame with infinite looping. The resulting GIF is 512 × 512 pixels and 1.8 seconds per cycle. No interpolation was added. This is a composed animation, not a native GIF returned by the model. ## Source and generation The source provides an original prompt; this production uses the separately recorded working prompt. [Source](https://developers.openai.com/api/docs/guides/image-prompting#generate-a-looping-gif). Source-post engagement does not measure this newly generated example. Generated with GPT Image 2.6. All reference images used here were generated for this project. ## Test prints ### 2026-11-04 · GPT Image 2.6 - Provider: OpenAI What we saw: Six distinct generated poses show the monkey raising and lowering the lantern and blinking. Cropped row-major into a 512px GIF, 300ms per frame, infinite loop; slight background drift between poses. This is a composed GIF, not native GIF output. #### Reference images 1. Original monkey reference ![Original monkey reference](https://promptseen.dev/media/a_383/image26-g01-monkey-raising-a-lantern-reference-detail-0db734cdabc1.webp) [Full-size image](https://promptseen.dev/media/a_383/image26-g01-monkey-raising-a-lantern-reference-original-0313551f1c19.png) #### Output ![Six distinct generated poses show the monkey raising and lowering the lantern and blinking.](https://promptseen.dev/media/a_382/image26-g01-monkey-raising-a-lantern-detail-a3b0c412c6e7.webp) ## Source and licence - Prompt: By Prompt Seen · Licence: CC BY 4.0 - Image: Creator: Prompt Seen · [Licence: CC BY 4.0](https://creativecommons.org/licenses/by/4.0/) · Generated image ## Inspiration & source evidence This prompt is an independent adaptation. The image shown here is our own recorded result. [OpenAI · OpenAI 官方指南](https://developers.openai.com/api/docs/guides/image-prompting#generate-a-looping-gif) · [Original source post; not this new generated output. Multiple cases from one post share the metrics.](https://developers.openai.com/api/docs/guides/image-prompting#generate-a-looping-gif) · Observed 2026-11-04 · [Prior research: direct page and visual review. Counts have not been refreshed.](https://developers.openai.com/api/docs/guides/image-prompting#generate-a-looping-gif) · The source provides an original prompt; this production uses the separately recorded working prompt. These figures belong to the original post or video. They are dated snapshots, not live counters or ratings of our image.