bulkgen

A build tool for AI-generated artifacts. Define image and text targets in a YAML config, and bulkgen handles dependency resolution, incremental builds, and parallel execution.

Uses Mistral for text generation and BlackForestLabs (FLUX) for image generation.

Installation

Requires Python 3.13+.

pip install .

Or with uv:

uv sync

Quick start

1. Set your API keys:

export MISTRAL_API_KEY="your-key"
export BFL_API_KEY="your-key"

2. Create a config file (e.g. my-project.bulkgen.yaml):

defaults:
  text_model: mistral-large-latest
  image_model: flux-pro

targets:
  hero.png:
    prompt: "A dramatic sunset over mountains, photorealistic"
    width: 1024
    height: 768

  blog-post.md:
    prompt: prompts/write-blog.txt
    inputs:
      - hero.png
      - notes.md

3. Build:

bulkgen build

Config format

The config file must be named <anything>.bulkgen.yaml and placed in your project directory. One config file per directory.

Top-level fields

Field	Description
defaults	Default model names (optional)
targets	Map of output filenames to their configuration

Defaults

defaults:
  text_model: mistral-large-latest   # used for .md, .txt targets
  image_model: flux-pro              # used for .png, .jpg, .jpeg, .webp targets

Target fields

Field	Type	Description
prompt	string	Inline prompt text, or path to a prompt file
model	string	Override the default model for this target
inputs	list[string]	Files this target depends on (other targets or existing files)
reference_image	string	Image file for image-to-image generation
control_images	list[string]	Control images (for canny/depth models)
width	int	Image width in pixels
height	int	Image height in pixels

Target type is inferred from the file extension:

• Image: .png, .jpg, .jpeg, .webp
• Text: .md, .txt

Prompts

Prompts can be inline strings or file references:

targets:
  # Inline prompt
  image.png:
    prompt: "A cat sitting on a windowsill"

  # File reference (reads the file contents as the prompt)
  article.md:
    prompt: prompts/article-prompt.txt

If the prompt value is a path to an existing file, its contents are read. Otherwise the string is used directly.

Dependencies

Targets can depend on other targets or on existing files in the project directory:

targets:
  base.png:
    prompt: "A landscape scene"

  variant.png:
    prompt: "Same scene but in winter"
    reference_image: base.png    # image-to-image, depends on base.png

  summary.md:
    prompt: "Summarize these notes"
    inputs:
      - base.png                 # depends on a generated target
      - research-notes.md        # depends on an existing file

bulkgen resolves dependencies automatically. If you build a single target, its transitive dependencies are included.

CLI

bulkgen build [target]

Build all targets, or a specific target and its dependencies.

• Skips targets that are already up to date (incremental builds)
• Runs independent targets in parallel
• Continues building if a target fails (dependents of the failed target are skipped)

bulkgen clean

Remove all generated target files and the build state file (.bulkgen.state.yaml). Input files are preserved.

bulkgen graph

Print the dependency graph showing build stages:

Stage 0 (inputs): research-notes.md
Stage 0 (targets): base.png
Stage 1 (targets): variant.png, summary.md
  variant.png <- base.png
  summary.md <- base.png, research-notes.md

Incremental builds

bulkgen tracks the state of each build in .bulkgen.state.yaml (auto-generated, add to .gitignore). A target is rebuilt when any of these change:

• Input file contents (SHA-256 hash)
• Prompt text
• Model name
• Extra parameters (width, height, etc.)

Environment variables

Variable	Required for
MISTRAL_API_KEY	Text targets (.md, .txt)
BFL_API_KEY	Image targets (.png, .jpg, .jpeg, .webp)