mAi
127bbf3ed5
internal/backend/comfyui.go implements the Backend interface against ComfyUI's /prompt + /history + /view HTTP API. Workflow is the canonical FLUX.1 schnell shape — UNETLoader + DualCLIPLoader (clip_l + t5xxl fp8) + VAELoader + ModelSamplingFlux + KSampler — assembled as a Go map per request so Width / Height / Seed / Steps / sampler / scheduler all flow into the right node inputs. Resilience: one retry on /prompt 5xx and transient network errors, no retry on 4xx. Connection-refused / timeouts surface a 'boot-whitetower mrock' hint. node_errors mentioning a missing unet point users at docs/setup-comfyui-mrock.md (matches both the 4xx and 200-with-errors shapes ComfyUI uses across versions). Result.Metadata carries model, seed_used, latency_ms, steps, sampler, scheduler, width, height, prompt_id, client_id, plus best-effort vram_used_mib pulled from /system_stats post-gen. Tests use httptest with poll interval squashed to 1ms — no real mRock dependency. Coverage: happy path, defaults, retry-once on 5xx, give-up after two 5xx, no-retry on 4xx, missing-model hint (both 4xx and 200+node_errors paths), history-error surfaced, /view 4xx, unreachable host, ctx cancel during poll, workflow-shape assertion, registration. Config sample: flux-schnell-local is now default_backend; the user-facing block names the unet file by basename (the mapping into models/unet/ is the server's convention, captured in docs/setup-comfyui-mrock.md from phase 1). Smoke verified end-to-end: imagen generate ... --backend flux-schnell-local --size 1024x1024 --output /tmp/cat-via-cli.png on mRock returned a 1024x1024 PNG of a cat in a fishbowl in 10.3s with a sidecar carrying seed + latency_ms + the rest of the metadata.
ImaGen
Model-agnostic image-generation framework: pluggable backends (local FLUX on mRock, Replicate, DALL-E, …) behind a single CLI / skill / API.
imagen generate "a cat in a fishbowl" --backend flux-schnell-local --size 1024x1024
See CLAUDE.md for the design — backend contract, registry,
config layout, how to add a new adapter.
Install
go install mgit.msbls.de/m/ImaGen/cmd/imagen@latest
Or from a checkout:
make build # writes ./bin/imagen
make install # installs into $GOBIN (defaults to ~/go/bin)
First run
mkdir -p ~/.config
imagen config init > ~/.config/imagen.yaml
imagen config validate
imagen backends
imagen generate "test prompt" --backend mock --output /tmp/x.png
The mock backend ships in this repo and produces a deterministic gradient PNG — useful for smoke-testing the pipeline without reaching any model.
Status
| Component | Status |
|---|---|
| Backend interface | done (#1) |
| Mock backend | done (#1) |
| ComfyUI / FLUX on mRock | open (#2) |
| Replicate adapter | open (#3) |
/imagine skill |
open (#4) |
| HTTP server | stubbed (#1) |
Issues live at https://mgit.msbls.de/m/ImaGen/issues.