SpaceSkills AI Filmmaking

Latte Art Coffee Making Process

Vlog / Daily Life Anime 2026-08-20

Latte Art Coffee Making Process preview

Footage © @aimikoda · View original post

The clip was published publicly by its creator and is linked here directly; rights holders may request removal.

Full prompt

MiniMax H3 with GPT Image 2 Storyboards

I think we can safely say storyboards work incredibly well with MiniMax H3. I'd definitely recommend adding storyboards to your workflow. I didn't include any scene descriptions in the video prompt at all. Its ability to understand reference images is really impressive.

MiniMax H3 Prompt for this video:
Use the storyboard  @[storyboard ref] as sequential shot guidance, not as a static image. Do not treat the storyboard as one image. Follow each panel as a separate beat. Use @[character ref] as character reference.

She talks while preparing the latte:

まずはエスプレッソを淹れます。
ミルクをなめらかにスチームして、ゆっくり注ぎます。

カップに近づけて、模様を描いていきます。

最後にひと仕上げ。ラテアートの完成です。

--

You can find storyboard and character image prompt in the replies.

### 作者补充

[补充1]
MiniMax H3 with GPT Image 2 Storyboards

I think we can safely say storyboards work incredibly well with MiniMax H3. I'd definitely recommend adding storyboards to your workflow. I didn't include any scene descriptions in the video prompt at all. Its ability to understand reference images is really impressive.

MiniMax H3 Prompt for this video:
Use the storyboard  @[storyboard ref] as sequential shot guidance, not as a static image. Do not treat the storyboard as one image. Follow each panel as a separate beat. Use @[character ref] as character reference.

She talks while preparing the latte:

まずはエスプレッソを淹れます。
ミルクをなめらかにスチームして、ゆっくり注ぎます。

カップに近づけて、模様を描いていきます。

最後にひと仕上げ。ラテアートの完成です。

--

You can find storyboard and character image prompt in the replies.

[补充2]
Midjourney v8.2 Prompt for character: Stylized female anime character, cafe barista, distinctive character-driven anime aesthetic, slightly unconventional facial proportions, sharp expressive eyes, delicate angular features, recognizable silhouette, clean background

GPT Image 2 Storyboard Prompt:
Create a 16:9, 9-panel storyboard for a quiet slice-of-life anime video about making latte and latte art. The uploaded character should appear throughout the storyboard. Use a basic Japanese animation storyboard sketch style with loose pencil lines, simple shading and cinematic anime compositions. The overall tone should feel intimate, understated and slightly melancholic, with late-evening café lighting, mundane moments made beautiful, subtle expressions, negative space, off-center framing and close-ups of hands, eyes, steam and small gestures. Avoid flashy commercial shots or exaggerated anime reactions. The character should softly talk to themselves while making the latte, with restrained natural body language. The latte design should gradually form but remain unreadable until the very end.
Narration:
まずはエスプレッソを淹れます。
ミルクをなめらかにスチームして、ゆっくり注ぎます。
カップに近づけて、模様を描いていきます。
最後にひと仕上げ。ラテアートの完成です。

Details

Target model MiniMax H3
Use case Vlog / Daily Life
Style Anime
Media Video
Duration 15.1s
Aspect ratio 1023:1150
Likes 627
Published 2026-08-20

Attribution

Author: @aimikoda · View original post

Prompts remain the copyright of their authors. We index and quote them with attribution plus a link to the original post; rights holders may request removal.

Run this prompt through the API

Copy the prompt above into a MiniMax H3 (Hailuo) text-to-video call to reproduce the shot. When adapting it, swap subject, setting and camera move one clause at a time. Access and licensing details are on About.

← Back to all prompts