Files
ImaGen/internal/config/config.go
mAi 8435817ce1 mAi: #10 - multi-model backend expansion (workflow templates + compare harness)
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.
2026-05-11 17:29:57 +02:00

236 lines
7.4 KiB
Go

// Package config loads ~/.config/imagen.yaml. The framework knows the global
// shape (default backend + output settings + a per-backend block); each
// adapter owns the schema of its own block.
package config
import (
"errors"
"fmt"
"os"
"path/filepath"
"gopkg.in/yaml.v3"
)
// Config is the top-level shape of imagen.yaml.
type Config struct {
DefaultBackend string `yaml:"default_backend"`
// OwnerUserID is m's auth.users.id on msupabase. The cloud-sync writer
// uses it to populate imagen.images.owner_user_id (NOT NULL, owns RLS).
// Empty disables DB inserts even when cloud_sync is on.
OwnerUserID string `yaml:"owner_user_id"`
Output OutputConfig `yaml:"output"`
Backends map[string]BackendSpec `yaml:"backends"`
}
// OutputConfig controls where generated images and metadata sidecars land,
// and whether `imagen generate` opens a tmux preview window.
type OutputConfig struct {
Directory string `yaml:"directory"`
Naming string `yaml:"naming"`
WriteMetadataJSON bool `yaml:"write_metadata_json"`
// Preview is the tri-state preview mode: "auto" (default), "on", "off".
// Empty / unset is treated as "auto". $IMAGEN_PREVIEW and the
// --preview/--no-preview flags override this in turn.
Preview string `yaml:"preview"`
// CloudSync controls whether successful generations also upload to
// Supabase Storage and insert into imagen.images. Tri-state mirroring
// Preview: "auto" (default — on when SUPABASE_URL + SUPABASE_SERVICE_KEY
// are set), "on" (errors if env unset), "off". --no-cloud overrides.
CloudSync string `yaml:"cloud_sync"`
}
// BackendSpec is one entry under `backends:`. Type identifies the adapter;
// the rest is opaque to the framework and handed to the adapter as-is.
type BackendSpec struct {
Type string `yaml:"type"`
Raw map[string]any `yaml:",inline"`
}
// DefaultPath returns ~/.config/imagen.yaml, honouring XDG_CONFIG_HOME.
func DefaultPath() (string, error) {
if x := os.Getenv("XDG_CONFIG_HOME"); x != "" {
return filepath.Join(x, "imagen.yaml"), nil
}
home, err := os.UserHomeDir()
if err != nil {
return "", err
}
return filepath.Join(home, ".config", "imagen.yaml"), nil
}
// Load reads and validates the config at path. If path is empty the default
// path is used. A missing file returns os.ErrNotExist so callers can decide
// whether to fall back to defaults.
func Load(path string) (*Config, error) {
if path == "" {
p, err := DefaultPath()
if err != nil {
return nil, err
}
path = p
}
data, err := os.ReadFile(path)
if err != nil {
return nil, err
}
cfg := &Config{}
if err := yaml.Unmarshal(data, cfg); err != nil {
return nil, fmt.Errorf("parse %s: %w", path, err)
}
if err := cfg.Validate(); err != nil {
return nil, fmt.Errorf("validate %s: %w", path, err)
}
return cfg, nil
}
// Validate enforces the framework-level invariants. Adapter-level validation
// happens when the adapter constructor runs.
func (c *Config) Validate() error {
if c.DefaultBackend != "" {
if _, ok := c.Backends[c.DefaultBackend]; !ok {
return fmt.Errorf("default_backend %q is not defined under backends:", c.DefaultBackend)
}
}
switch c.Output.Preview {
case "", "auto", "on", "off":
default:
return fmt.Errorf("output.preview = %q (must be auto|on|off)", c.Output.Preview)
}
switch c.Output.CloudSync {
case "", "auto", "on", "off":
default:
return fmt.Errorf("output.cloud_sync = %q (must be auto|on|off)", c.Output.CloudSync)
}
for name, spec := range c.Backends {
if name == "" {
return errors.New("empty backend name")
}
if spec.Type == "" {
return fmt.Errorf("backend %q is missing a type:", name)
}
}
return nil
}
// Sample is the canonical example written by `imagen config init`.
const Sample = `# imagen.yaml — config for the imagen CLI.
# Adapters get only their own sub-block at construction. Add a new backend by
# implementing the Backend interface, registering its type name, and listing
# an instance here.
default_backend: flux-schnell-local
# Owner UUID for the cloud-sync row in imagen.images. Look up via:
# SELECT id FROM auth.users WHERE email = '<your-supabase-email>';
# Empty disables imagen.images inserts even when cloud_sync is on.
owner_user_id: ""
output:
directory: ~/Pictures/imagen
naming: "{date}-{slug}-{seed}.png"
write_metadata_json: true
# Open a tmux window with tmux-img after a successful generation.
# auto (default): preview iff stdout is a TTY and $TMUX is set.
# on: always preview (errors outside a tmux session).
# off: never preview (use this for batch / CI callers).
preview: auto
# Sync the PNG to Supabase Storage (bucket: imagen-generated) and insert
# a row into imagen.images. Reads SUPABASE_URL + SUPABASE_SERVICE_KEY
# from env (same as mai.imagen_usage cost-tracking).
# auto (default): on iff env is configured AND owner_user_id is set.
# on: always upload (errors if env or owner_user_id is missing).
# off: never upload. --no-cloud also forces off per-call.
cloud_sync: auto
backends:
# FLUX.1-schnell on the local ComfyUI server. The "workflow" key picks the
# bundled template under internal/backend/workflows/; omit it for back-compat
# (defaults to flux1-schnell). See docs/backends.md for the per-model setup.
flux-schnell-local:
type: comfyui
base_url: http://mrock:8188
workflow: flux1-schnell
# Filename of the unet checkpoint inside the ComfyUI server's
# models/unet/ directory.
model: flux1-schnell.safetensors
vae: ae.safetensors
clip_l: clip_l.safetensors
clip_t5: t5xxl_fp8_e4m3fn.safetensors
dtype: fp8_e4m3fn
default_steps: 4
default_sampler: euler
default_scheduler: simple
default_cfg: 1.0
# FLUX.2 [klein] 4B distilled — sub-second on RTX 4070 Ti SUPER.
# Weights: BFL non-commercial; flux-2-klein-base-4b-fp8 in models/unet/,
# qwen_3_4b in models/text_encoders/, flux2-vae in models/vae/.
flux2-klein-local:
type: comfyui
base_url: http://mrock:8188
workflow: flux2-klein
model: flux-2-klein-base-4b-fp8.safetensors
vae: flux2-vae.safetensors
clip: qwen_3_4b.safetensors
dtype: fp8_e4m3fn
default_steps: 4
default_sampler: euler
default_scheduler: simple
default_cfg: 1.0
guidance: 4.0
# SD3.5 medium — single-checkpoint variant that bundles the three text
# encoders inside the .safetensors. Drop into models/checkpoints/.
sd35-medium-local:
type: comfyui
base_url: http://mrock:8188
workflow: sd35-medium
model: sd3.5_medium_incl_clips_t5xxlfp8scaled.safetensors
default_steps: 28
default_sampler: dpmpp_2m
default_scheduler: sgm_uniform
default_cfg: 4.5
shift: 3.0
mock:
type: mock
flux-schnell-replicate:
type: replicate
api_token_env: REPLICATE_API_TOKEN
model: black-forest-labs/flux-schnell
default_steps: 4
default_aspect_ratio: "1:1"
flux-dev-replicate:
type: replicate
api_token_env: REPLICATE_API_TOKEN
model: black-forest-labs/flux-dev
default_steps: 28
default_aspect_ratio: "1:1"
dalle3:
type: openai
api_key_env: OPENAI_API_KEY
model: dall-e-3
`
// ExpandPath resolves leading ~ to the user's home directory.
func ExpandPath(p string) string {
if p == "" || p[0] != '~' {
return p
}
home, err := os.UserHomeDir()
if err != nil {
return p
}
if len(p) == 1 {
return home
}
if p[1] == '/' {
return filepath.Join(home, p[2:])
}
return p
}