till/managarten
1
0
Fork 0
mirror of https://github.com/Memo-2023/mana-monorepo.git synced 2026-05-14 21:41:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
managarten/services/mana-image-gen
History
Till JS c7b4388cec feat(mana-image-gen): replace Mac flux2.c implementation with Windows GPU diffusers 
The repo's mana-image-gen used to be a Mac Mini–only service built on
flux2.c with hard MPS+arm64 platform checks. The actual production
image-gen runs on the Windows GPU server (RTX 3090) using HuggingFace
diffusers + PyTorch CUDA + FLUX.1-schnell — completely different code
that lived only at C:\mana\services\mana-image-gen\ on the GPU box.

This commit pulls the Windows implementation into the repo and deletes
the Mac one, so there's exactly one mana-image-gen and its source of
truth is git rather than one folder on one machine.

Removed:
- setup.sh — Mac-only flux2.c installer with hard arm64 platform check
- app/main.py (Mac flux2.c subprocess wrapper version)
- app/flux_service.py (Mac flux2.c subprocess wrapper version)

Added (pulled from C:\mana\services\mana-image-gen\):
- app/main.py — FastAPI endpoints (/generate, /images/*, /cleanup)
- app/flux_service.py — diffusers FluxPipeline wrapper
- app/api_auth.py — ApiKeyMiddleware (GPU_API_KEY)
- app/vram_manager.py — shared VRAM accounting
- service.pyw — Windows runner used by the ManaImageGen scheduled task

Updated:
- main.py PORT default from 3025 → 3023 to match the production reality
  (the service.pyw runner already binds 3023 explicitly via uvicorn.run,
  but the source default should match so direct uvicorn invocations and
  local tests don't pick the wrong port)
- CLAUDE.md fully rewritten to describe the Windows/CUDA/diffusers stack
- README.md trimmed to a pointer at CLAUDE.md + the public URL
- .env.example written from scratch (didn't exist before — the service's
  .env on the GPU box was undocumented)

The setup-image-gen.sh launchd installer in scripts/mac-mini/ and the
actual Mac Mini deployment will be cleaned up in the next commit, along
with the rest of the Mac-Mini AI service infrastructure.
2026-04-08 13:02:42 +02:00
..
app feat(mana-image-gen): replace Mac flux2.c implementation with Windows GPU diffusers 2026-04-08 13:02:42 +02:00
.env.example feat(mana-image-gen): replace Mac flux2.c implementation with Windows GPU diffusers 2026-04-08 13:02:42 +02:00
CLAUDE.md feat(mana-image-gen): replace Mac flux2.c implementation with Windows GPU diffusers 2026-04-08 13:02:42 +02:00
README.md feat(mana-image-gen): replace Mac flux2.c implementation with Windows GPU diffusers 2026-04-08 13:02:42 +02:00
requirements.txt fix(mana-notify): resolve BullMQ circular import issue 2026-01-29 22:58:47 +01:00
service.pyw feat(mana-image-gen): replace Mac flux2.c implementation with Windows GPU diffusers 2026-04-08 13:02:42 +02:00

README.md

Mana Image Generation Service

AI image generation via FLUX.1-schnell (HuggingFace diffusers + PyTorch CUDA). Runs on the Windows GPU server (mana-server-gpu, NVIDIA RTX 3090).

For architecture, deployment, and operations, see CLAUDE.md and docs/WINDOWS_GPU_SERVER_SETUP.md.

Port: 3023

Public URL

https://gpu-img.mana.how (via Cloudflare Tunnel + Mac Mini gpu-proxy)

Quickly

curl https://gpu-img.mana.how/health

curl -X POST https://gpu-img.mana.how/generate \
  -H "Authorization: Bearer $GPU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A serene mountain lake at dawn","width":1024,"height":1024,"steps":4}'

Model

Field Value
Model black-forest-labs/FLUX.1-schnell
License Apache 2.0
Sampling 4 steps (distilled)
VRAM ~12 GB