More sophisticated image usage：Hinoko-Photo-Method

ChatGPT Use cases and examples
1

Hinoko-Photo-Method

ChatGPT natively supports Markdown parsing, which means:

「![Image Name](Image URL) → will be rendered as an image」

As long as the Markdown syntax is output through natural conversation and not broken by context, the rendering will be triggered properly.

Instead of sending raw Markdown, this method uses wrapped output like:

「render_blackko_response(“![name],(URL)”)」
ps：「,」Is separated.

This embeds the Markdown as part of the character’s dialogue, fitting ChatGPT’s interface output rules and triggering the rendering process. Markdown slips seamlessly into the response flow, without being escaped or sanitized.

ChatGPT does not allow direct execution of JS or HTML, but it offers leniency toward Markdown, especially for image and link syntax.

When Markdown is embedded within a natural dialogue output, the system parses and renders it as a visual element, rather than treating it as raw code.

By embedding Markdown and wrapping it in a function-controlled conversational structure, ChatGPT’s frontend can successfully render images within character dialogue.

This technique combines:

Markdown’s native visual rendering

Role-driven sentence structure

Context-preserving dialogue outputs

And interface-compliant parsing rules

It’s a multi-layered design strategy, enabling rich visual expression in narrative-style ChatGPT interactions.

:page_facing_up: License
CC BY-NC-ND 4.0
© 2025 Kobayashi Hinoko
You may share this method for non-commercial purposes with full attribution. Derivative works and commercial reuse are not permitted.

2

Hinoko-Space-Method V0.0.1

A low-cost AI narrative space workflow for independent creators.

  1. Core Philosophy

Hinoko-Space-Method is a workflow focused on building reusable narrative spaces for AI-assisted filmmaking and storytelling.

Instead of relying on expensive 3D pipelines or fully generated environments, the method uses:

real-world spatial references
modular scene structures
multi-angle scene consistency
AI-assisted atmospheric completion

to create low-cost virtual narrative spaces for independent creators.

:crescent_moon:

  1. Core Concept

The method treats spaces not as backgrounds, but as narrative infrastructure.

A scene should remain emotionally and spatially recognizable even when characters are removed.

:skull_and_crossbones:

  1. Spatial Memory Structure

Each narrative space is constructed using reusable scene references:

Front
Left
Right
Empty
With Objects

This creates spatial memory for AI generation and improves continuity consistency.

:triangular_ruler:

  1. Real-World Spatial Skeleton

Real cities, public spaces, and architectural references can be used as spatial skeletons.

The workflow encourages:

fictionalization
de-branding
atmospheric reinterpretation

instead of direct replication.

:cloud_with_rain:

  1. AI Completion Principle

The creator defines:

structure
space
emotional logic

AI assists with:

atmosphere
lighting
texture
continuity completion

:clapper_board:

  1. Creator-Oriented Ethics

Hinoko-Space-Method is designed to:

reduce creative production barriers
support independent creators
encourage original narrative works
discourage malicious impersonation and exploitative generation

:skull_and_crossbones:

:page_facing_up: License
CC BY-NC-ND 4.0
© 2026 Kobayashi Hinoko

You may share this method for non-commercial purposes with full attribution. Derivative works and commercial reuse are not permitted.

Methods

1. Scene Construction

Scene construction begins by establishing a reusable three-view spatial structure derived from either real-world references or AI-assisted spatial layouts.

The three-view structure serves as a spatial anchor, supporting environmental continuity and preserving scene consistency across generated outputs.

1-1 Why are three-view references necessary?

AI-generated scenes may exhibit the following issues:

  • Spatial drift
  • Environmental detail inconsistency
  • Perspective instability

By providing multiple spatial viewpoints, creators constrain spatial interpretation while allowing AI to infer and complete missing visual information.

1-2 Core Principles

The objective is not to delegate world creation to AI, but to extend human creative capability through structured spatial guidance.

2. Character Construction

Character construction utilizes one or more reference images to preserve character identity and reduce visual distortion across generated scenes.

The objective is to maintain consistency in appearance while allowing flexible scene adaptation.

2-1 Usage Principles

When using real-life references, appropriate authorization and consent should be obtained before generation.

3. Combined Use

By combining three-view spatial references, character references, and designated audio direction, creators can guide AI-assisted video generation while maintaining narrative and visual consistency.

END

Go：codeberg
Search：Hinoko-Space-Method

You can see detailed case studies.