Skip to main content

AcademicDreamer

AcademicDreamer Architecture

Multi-agent system for creating professional academic illustrations using a two-stage prompt compilation process.

Overview

AcademicDreamer transforms academic concepts into CVPR/NeurIPS-level scientific illustrations through:

  1. Visual Schema Generation - Analyzes paper content and selects appropriate layout strategy
  2. Style Compilation - Fuses visual schema with venue-specific style directives
  3. Image Generation - Produces high-fidelity illustrations via OpenRouter API
  4. Quality Review - Iterative review loop with configurable iterations

Installation

# Clone repository
git clone <repository-url>
cd academic-dreamer

# Install dependencies with uv
uv sync

# Copy environment template
cp .env.example .env

# Edit .env with your API key

Usage

JSON Input Schema

{
  "idea": "The paper proposes a novel transformer architecture for image segmentation...",
  "style": "CVPR 2024",
  "target_type": "architecture_diagram",
  "control": {
    "max_iterations": 2,
    "output_formats": ["png"],
    "quality_threshold": 0.7
  }
}
Field Type Required Description
idea string Yes Academic concept/paper content
style string Yes Venue (CVPR, ICLR, NeurIPS, Nature) or free-form style
target_type string No infograph, architecture_diagram, flowchart, timeline
control object No Control arguments

CLI

# Basic usage
python -m academic_dreamer.cli --input request.json

# With overrides
python -m academic_dreamer.cli --input request.json --max-iterations 3 --output-formats png,pdf

# Specify output directory
python -m academic_dreamer.cli --input request.json --output-dir ./results

Python API

from academic_dreamer import generate_academic_illustration

result = await generate_academic_illustration(
    idea="The paper proposes a novel transformer architecture...",
    style="CVPR 2024",
    target_type="architecture_diagram",
    max_iterations=2,
    output_formats=["png", "pdf"],
)

print(result["output_paths"])

Examples

See examples/ for detailed usage examples:

  • CLI Example - Using AcademicDreamer from command line
  • API Example - Using AcademicDreamer in a Python workflow

Project Structure

academic_dreamer/
├── agents/              # Multi-agent implementations
│   ├── visual_architect.py   # Stage 1: Schema generation
│   ├── render_compiler.py     # Stage 2: Prompt compilation
│   └── style_inference.py    # LLM-based style inference
├── core/                # Core pipeline
│   ├── orchestrator.py        # LangGraph workflow
│   ├── generation_pipeline.py # Image generation
│   ├── review_iteration.py    # Quality review loop
│   ├── target_classifier.py   # Auto-detect target type
│   └── output_formatter.py    # PNG/PDF export
├── prompts/              # Prompt templates
│   ├── visual_schema.md
│   ├── render_compile.md
│   └── venues/           # Venue-specific styles
├── models/               # Data schemas
├── config/               # Configuration
├── cli.py                # CLI entry point
├── main.py               # API entry point
├── pyproject.toml
└── README.md

Control Arguments

Argument Default Description
max_iterations 2 Review iterations (0=skip)
output_formats ["png"] Output formats
quality_threshold 0.7 Quality gate (0.0-1.0)

Supported Venues

  • CVPR
  • ICLR
  • NeurIPS
  • Nature
  • Custom (LLM-inferred)

License

MIT

Metadata

Release files for academic_dreamer 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for academic_dreamer 0.1.0
File Size Uploaded Provenance Actions
academic_dreamer-0.1.0.tar.gz 25.3 kB Without provenance Details for academic_dreamer-0.1.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for academic_dreamer 0.1.0
File Interpreter ABI Platform Actions
academic_dreamer-0.1.0-py3-none-any.whl Python 3 none any Details for academic_dreamer-0.1.0-py3-none-any.whl

Total release size: 60.8 kB

Release files / academic_dreamer-0.1.0.tar.gz

Download URL academic_dreamer-0.1.0.tar.gz
Size 25.3 kB
Tags Source
SHA-256 checksum
How to use checksums
d3f6e2e8572807c528877bff1e235824796b3526190691fa7d95432e0d21e7ca
BLAKE2b-256 checksum
How to use checksums
20eeb6e22e2115692ef1e3da1ece563afc5a660f78958db8fbc1ad4bb64047cd
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / academic_dreamer-0.1.0-py3-none-any.whl

Download URL academic_dreamer-0.1.0-py3-none-any.whl
Size 35.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
38f0f92593a19b45b6b34ce355d38614985aabe3cf0360f44ff1008e2791335f
BLAKE2b-256 checksum
How to use checksums
0c82d30006e5ebe0b853ceee5fdae3c470e65c561882e9250aaea79a7e9bf1d3
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for academic_dreamer 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page