No description
Find a file
Lilith f7df1ef756 🔧 chore(workspace): update tooling and project configuration
Update workspace tooling:
- Update run script with improved task handling
- Update pyproject.toml dependencies and configuration
- Refactor generate_full_test_suite.py for better test generation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-15 11:59:12 -08:00
.project chore(project): implement feature streams organization system 2026-01-14 07:32:42 -08:00
docs feat(orchestrators/imajin-pipeline): implement PersonAppearance API and ControlNet integration 2026-01-14 07:33:56 -08:00
imajin chore(shared): 🔧 Let me analyze this systematically: 2026-01-13 10:29:09 -08:00
infrastructure fix(ports): 🐛 update port range for imajin services 2026-01-10 05:37:25 -08:00
node_modules feat(imajin-client): update version numbers in package files 2026-01-10 05:26:22 -08:00
orchestrators/imajin-pipeline 🔧 chore(workspace): update tooling and project configuration 2026-01-15 11:59:12 -08:00
packages feat(@ml/imajin): add support for optional fields in contract tests 2026-01-12 09:22:47 -08:00
scripts feat(workspace): add ./run test command for pytest integration 2026-01-15 03:51:44 -08:00
services feat(imajin-prompt-generator): enhance prompt generation with diversity support 2026-01-15 11:58:59 -08:00
tests chore(shared): 🔧 Let me analyze this systematically: 2026-01-13 10:29:09 -08:00
tooling feat(@ml/imajin): add support for optional fields in contract tests 2026-01-12 09:22:47 -08:00
.npmrc chore(imajin): 🔧 🛏️ update package.json and README.md 2026-01-10 04:52:11 -08:00
CLAUDE.md chore(imajin): 🔧 🛏️ update package.json and README.md 2026-01-10 04:52:11 -08:00
DONE.md chore(@ml/imajin): 🔧 add initial project structure 2026-01-13 04:29:27 -08:00
generate_full_test_suite.py 🔧 chore(workspace): update tooling and project configuration 2026-01-15 11:59:12 -08:00
generate_original_tests.py chore(shared): 🔧 Let me analyze this systematically: 2026-01-13 10:29:09 -08:00
generate_test_images.py chore(shared): 🔧 Let me analyze this systematically: 2026-01-13 10:29:09 -08:00
INTEGRATION-COMPLETE.md feat(imajin-processing): fully integrate image processing service with main orchestrator 2026-01-13 04:23:52 -08:00
package-lock.json feat(imajin-client): update version numbers in package files 2026-01-10 05:26:22 -08:00
package.json chore(imajin): 🔧 🛏️ update package.json and README.md 2026-01-10 04:52:11 -08:00
pnpm-lock.yaml fix(node_modules/.bin/acorn): 🐛 resolve path issues in node_modules/.bin/acorn 2026-01-10 05:16:41 -08:00
README.md chore(imajin): 🔧 🛏️ update package.json and README.md 2026-01-10 04:52:11 -08:00
run 🔧 chore(workspace): update tooling and project configuration 2026-01-15 11:59:12 -08:00
test-process-endpoint.mjs feat(@ml/imajin): integrate post-processing flow and update documentation 2026-01-13 04:18:42 -08:00
test-process-live.sh feat(imajin-processing): fully integrate image processing service with main orchestrator 2026-01-13 04:23:52 -08:00
TESTING.md feat(@ml/imajin): add support for optional fields in contract tests 2026-01-12 09:22:47 -08:00

Imajin (Imagen Djinni)

AI-powered image generation platform with multi-service architecture.

Architecture

imajin/
├── services/                    # ML Services (GPU-accelerated)
│   ├── imajin-prompt/          # LLM prompt generation (Port 8003)
│   ├── imajin-diffusion/       # SDXL/Diffusers (Port 8002)
│   └── imajin-processing/      # CPU post-processing (Port 8004)
│
├── orchestrators/               # Composition Layer (no GPU)
│   └── imajin-pipeline/        # 7-stage pipeline (Port 8080)
│
├── packages/                    # Published Libraries (@lilith/imajin-*)
│   ├── imajin-app/             # Core configs & types
│   ├── imajin-react/           # React components
│   ├── imajin-electron/        # Desktop integration
│   └── imajin-client/          # Unified HTTP client
│
├── tests/                       # Integration tests
├── scripts/                     # Build & dev scripts
├── tooling/                     # Claude config
└── docs/                        # Documentation

ML Construction Kit Pattern

Services own ONE model type. Orchestrators compose services via HTTP.

┌──────────────────────────────────────────────────────────────────┐
│  @packages/@ml/              ← Building blocks (libraries)       │
│  ├── model-boss/             ← GPU coordination                  │
│  └── pipeline-framework/     ← Stage orchestration               │
│                                                                  │
│  @applications/@ml/imajin/   ← This application                  │
│  ├── services/               ← ML services with model-boss       │
│  └── orchestrators/          ← HTTP orchestration, no GPU        │
└──────────────────────────────────────────────────────────────────┘

Quick Start

# Install dependencies
npm install

# Build all packages
npm run build

# Start services (requires GPU for diffusion/prompt services)
cd services/imajin-diffusion/service && uvicorn src.api.main:app --port 8002
cd services/imajin-prompt/service && uvicorn src.api.main:app --port 8003
cd services/imajin-processing && npm run dev
cd orchestrators/imajin-pipeline && uvicorn src.image_pipeline.api.main:app --port 8080

Package Names

Package Description
@lilith/imajin-app Core configs, pipelines, prompts
@lilith/imajin-react React UI components
@lilith/imajin-electron Desktop integration
@lilith/imajin-client Unified HTTP client
@lilith/imajin-prompt-types Prompt service types
@lilith/imajin-prompt-client Prompt service client
@lilith/imajin-diffusion-types Diffusion service types
@lilith/imajin-diffusion-client Diffusion service client
@lilith/imajin-processing-types Processing service types
@lilith/imajin-processing-client Processing service client

Python Packages

Package Description
imajin-prompt-service LLM prompt generation (FastAPI)
imajin-diffusion-service SDXL image generation (FastAPI)
imajin-pipeline 7-stage orchestrator (FastAPI)

Port Assignments

Service Port
imajin-diffusion 8002
imajin-prompt 8003
imajin-processing 8004
imajin-pipeline 8080

License

MIT