图片和演示归原作者所有,本页仅作截图预览与整理。
灰色走廊 GIF 交给 Minimax H3 做成 15 秒视频
先用 ChatGPT Images 2.6 做出约 15 秒灰度 GIF 运动草稿,再经 Maestro 交给 Minimax H3 生成带音频的成品视频。
这条按原帖整理为混用工作流:分步写明哪一步用了 GPT Image 2.6,哪一步用了其他工具。原帖没写清的步骤保留「原帖未说明」。本站未独立复现。


分步流程
下面按原帖已有的说明排列。写到 GPT Image 2.6 的步骤就是用它出图或做参考的步骤,其余步骤使用原帖点名的其他工具。
第1步:在 ChatGPT(GPT Image 2.6)上先生成一段 5 秒、10 帧、看起来像粗糙灰色 Blender 视口的动画 GIF。提示词已公开,见 prompt 字段。
第2步:继续让 ChatGPT 尽量延长这段 GIF。作者说模型有时会截断,并从上一份 GIF 的最后一帧另开一段;之后再让 ChatGPT 用内部工具把多段合成一条约 15 秒的 GIF。
第3步:在 Maestro 里把这条 15 秒 GIF 作为参考视频交给 Minimax H3(作者用的是 Minimax H3 Singularity 4 step、480p)生成带音频的成片。作者注明也可用任何支持参考视频的 AI 视频工具。
展开 H3 公开的提示词
Transform the reference video into Doom 2 style video game recording. a mancubus monster from the video game doom emerges from a doorway and slowly approaches the camera. The Mancubus is a grotesque, morbidly obese demon with a tusked face whose forearms are completely replaced by massive cybernetic rocket launchers. The camera suddenly jerks to the right, falls to the floor, and lands sideways. The creature approaches, crouches down, reaches toward the lens, and picks up the gun and takes it away, and walks back behind the door, disappearing.. The viewpoint turns smoothly to left, revealing an impossibly enormous pool of lava stretching endlessly into darkness, repetitive pillars, and hell scape, with grotesque hell sound. Everything should feel unsettlingly real, with authentic analog tape noise, imperfect autofocus, natural handheld movement, eerie fluorescent humming, echoing footsteps, and distant water sounds. Preserve the exact camera movements, character actions, spatial relationships, and sequence of events from the reference video in one continuous, uninterrupted shot, with no cuts, dialogue, music, or jump scares.
做法
作者在主帖写明两步:在 ChatGPT 上做 15 秒 GIF,再经 Maestro 喂给 Minimax H3。线程里拆成更细的三步,并公开了 GIF 与 H3 提示词。左侧是 GIF,右侧是成片。
用到的工具
- ChatGPT Images 2.6
- Minimax H3 Singularity
- Maestro
提示词
展开公开提示词
此为作者回复中公开的 GPT Image 2.6 / ChatGPT 5 秒灰度 GIF 提示词。Minimax H3 视频提示词见同串 Step 3,已写入 workflow。
Generate a 5-second animated GIF consisting of 10 evenly spaced animation frames. Make it look like a crude gray Blender viewport animation, not cinematic footage. A single continuous shot inside a rectangular hallway with a tiled floor and simple gray walls. The camera slowly advances toward a doorway. A black humanoid mannequin with unusually long arms emerges from behind the doorway. The camera suddenly whips right, falls onto its side, and stops. The mannequin slowly walks toward and past the fallen camera. Maintain consistent 3D geometry, character proportions, doorway placement, and spatial relationships. No cuts, no teleportation, no scene changes, no added props. Focus on exact camera movement, depth, and timing. The animation should play once as a complete sequence, not return to its starting pose.
这里只收原帖已经公开的内容。上下文和后续修改以原帖为准。
在原帖查看 ↗(新窗口)相关链接
整理备注:混用工作流,版权归原作者。
