Path 1 architecture: one comfyui adapter, workflows as data.
- workflow_template.go: embed.FS + token substitution with type-preserving
whole-value placeholders. ${prompt} → string, ${seed} → int64,
${cfg} → float64 — no JSON round-tripping. Partial matches ignored.
- comfyui.go: refactored to load workflow from embedded FS or filesystem
path. Back-compat preserved: workflow: defaults to flux1-schnell.
- workflows/{flux1-schnell,flux2-klein,sd35-medium}.json — bundled
templates. flux1-schnell migrated from hardcoded with identical node IDs.
- compare.go: new `imagen compare` subcommand. Sequential N-backend run
(one GPU on mRock — parallel would OOM), per-backend PNG, sidecar JSON
with per-model metadata + errors, composite contact sheet via Go image
package (no ImageMagick dep).
- Sample config gains flux2-klein-local + sd35-medium-local instances.
- docs/backends.md: architecture rationale + per-model HF download paths
+ how to add a new bundled workflow + compare-harness reference.
Live smoke verified: compare mock + flux-schnell-local at 768×768 →
both PNGs written, sidecar JSON has workflow="flux1-schnell" + full
metadata, contact sheet renders. Worker contract (Request → Generate)
unchanged, so flexsiebels /imagine UI API surface preserved.
Tests: 11 existing comfyui + 6 new workflow_template + 5 new compare
tests, all green.
Adding a new model is now yaml + JSON, never Go.
Implements the Replicate API backend (FLUX schnell / FLUX dev) per ImaGen
issue #3:
- internal/backend/replicate.go — Backend adapter. Supports model
refs as "owner/name" (uses /v1/models/{owner}/{name}/predictions) and
"owner/name:hash" (uses /v1/predictions with explicit version). Polls
/v1/predictions/{id} every 500ms with model-aware timeout (60s schnell,
120s dev). Resilience: 401 names api_token_env, 429 with exp backoff
up to 3 retries (honours Retry-After), 5xx retries once, image
download retries once on transient failure.
- internal/backend/replicate_pricing.go — hardcoded per-image USD rates
for known FLUX models, snapshotted from replicate.com/pricing with a
refresh TODO.
- internal/backend/replicate_test.go — mocked-HTTP unit tests covering
happy path (model + version-pinned), 401, 429 retry policy, failed
prediction, poll timeout, image-download retry, ctx cancel, BackendOpts
passthrough, default_steps, aspect-ratio reduction, sha256 prompt hash.
- internal/usage/usage.go — Supabase REST sink + read-side query for
mai.imagen_usage. Adapter writes are best-effort: failures warn but
the image still lands.
- cmd/imagen/usage.go — `imagen usage [--since DATE] [--raw]` reads
the table and prints a tab-aligned grouped or raw table with totals.
- cmd/imagen/backends.go — instances of type=replicate now report
"ok" or "not configured (set REPLICATE_API_TOKEN)" depending on env.
- internal/config/config.go — sample adds flux-schnell-replicate +
flux-dev-replicate; default_backend stays flux-schnell-local.
- Supabase migration mai.imagen_usage (id, created_at, backend, model,
seed, prompt_hash, latency_ms, cost_usd_estimate, caller) + indexes
on (created_at DESC) and (caller). The raw prompt is never stored.
Caller identity resolves from MAI_FROM_ID, then the tmux pane's
@mai-name option, mirroring the maimcp identity logic. Prompt hash is
sha256 of the user-facing prompt; raw prompt never reaches the table.
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.
