Merge mai/hermes/issue-10-multi-model: multi-model backend expansion + compare harness (#10)

This commit is contained in:
mAi
2026-05-11 17:32:36 +02:00
15 changed files with 1638 additions and 122 deletions

386
cmd/imagen/compare.go Normal file
View File

@@ -0,0 +1,386 @@
package main
import (
"context"
"encoding/json"
"flag"
"fmt"
"image"
"image/color"
"image/draw"
"image/png"
"io"
"os"
"path/filepath"
"sort"
"strings"
"time"
"golang.org/x/image/font"
"golang.org/x/image/font/basicfont"
"golang.org/x/image/math/fixed"
"mgit.msbls.de/m/ImaGen/internal/backend"
"mgit.msbls.de/m/ImaGen/internal/config"
"mgit.msbls.de/m/ImaGen/internal/output"
"mgit.msbls.de/m/ImaGen/internal/prompt"
)
// runCompare implements `imagen compare "<prompt>" --models a,b,c --output <dir>`.
//
// Each backend in --models runs sequentially against the same prompt (mRock
// has a single GPU; parallelising would just OOM). Each generation lands as
// a backend-suffixed file in the output dir; a contact sheet stitches them
// together into one PNG with the backend name overlaid on each cell. A
// sidecar JSON next to the contact sheet lists every generation with its
// per-model metadata (latency, seed, model file, VRAM peak).
func runCompare(ctx context.Context, args []string) error {
fs := flag.NewFlagSet("compare", flag.ContinueOnError)
var (
modelsCSV string
size string
outDir string
style string
negative string
seed int64
steps int
configPath string
noContact bool
)
fs.StringVar(&modelsCSV, "models", "", "comma-separated backend instance names (required)")
fs.StringVar(&size, "size", "1024x1024", "WxH for every backend")
fs.StringVar(&outDir, "output", "", "directory to write the images + contact sheet (default: ~/Pictures/imagen/compare)")
fs.StringVar(&style, "style", "", "style preset applied to the prompt before dispatching to each backend")
fs.StringVar(&negative, "negative", "", "negative prompt (forwarded to every backend that supports it)")
fs.Int64Var(&seed, "seed", 0, "deterministic seed for every backend (0 = each backend rolls its own)")
fs.IntVar(&steps, "steps", 0, "diffusion steps (0 = each backend's default)")
fs.StringVar(&configPath, "config", "", "config file path (default: ~/.config/imagen.yaml)")
fs.BoolVar(&noContact, "no-contact-sheet", false, "skip the composite PNG; only write per-backend images + sidecar")
fs.Usage = func() {
fmt.Fprintln(fs.Output(), `Usage: imagen compare "<prompt>" --models a,b,c [flags]`)
fs.PrintDefaults()
}
leadingPositional, flagArgs := splitLeadingPositional(args)
if err := fs.Parse(flagArgs); err != nil {
return err
}
positional := append(leadingPositional, fs.Args()...)
if len(positional) == 0 {
fs.Usage()
return userErr("missing prompt")
}
rawPrompt := strings.Join(positional, " ")
modelNames := splitCSV(modelsCSV)
if len(modelNames) == 0 {
return userErr("--models is required (comma-separated backend instance names)")
}
w, h, err := parseSize(size)
if err != nil {
return userErr("bad --size: %v", err)
}
cfg, cfgErr := config.Load(configPath)
if cfgErr != nil && !os.IsNotExist(cfgErr) {
return cfgErr
}
if outDir == "" {
home, _ := os.UserHomeDir()
outDir = filepath.Join(home, "Pictures", "imagen", "compare")
}
outDir = config.ExpandPath(outDir)
finalPrompt, err := prompt.Apply(rawPrompt, style)
if err != nil {
return userErr("%v", err)
}
runID := time.Now().Format("20060102-150405")
runDir := filepath.Join(outDir, runID+"-"+output.Slug(rawPrompt))
if err := os.MkdirAll(runDir, 0o755); err != nil {
return fmt.Errorf("mkdir %s: %w", runDir, err)
}
results := make([]compareResult, 0, len(modelNames))
for i, name := range modelNames {
fmt.Fprintf(os.Stderr, "[%d/%d] %s ...\n", i+1, len(modelNames), name)
res, err := generateOne(ctx, cfg, name, finalPrompt, negative, w, h, seed, steps, runDir, rawPrompt)
if err != nil {
// Don't abort the whole run on a single backend failure — record
// the error and continue. flexsiebels-style consumers want to
// see N-1 results rather than zero when one model is offline.
fmt.Fprintf(os.Stderr, " failed: %v\n", err)
results = append(results, compareResult{Backend: name, Error: err.Error()})
continue
}
fmt.Fprintf(os.Stderr, " %s (%d ms)\n", res.ImagePath, res.LatencyMs)
results = append(results, res)
}
// Sidecar JSON beside the run dir captures every attempt.
sidecar := filepath.Join(runDir, "compare.json")
if err := writeCompareSidecar(sidecar, rawPrompt, style, negative, w, h, seed, steps, results); err != nil {
return err
}
fmt.Fprintln(os.Stderr, "sidecar:", sidecar)
// Contact sheet stitches the successful results together. If every
// backend failed there's nothing to draw, so skip silently.
if !noContact {
successes := successfulResults(results)
if len(successes) > 0 {
sheet := filepath.Join(runDir, "contact-sheet.png")
if err := writeContactSheet(sheet, rawPrompt, successes); err != nil {
return fmt.Errorf("contact sheet: %w", err)
}
fmt.Println(sheet)
} else {
fmt.Fprintln(os.Stderr, "imagen compare: all backends failed; no contact sheet written")
}
}
return nil
}
// compareResult is one backend's output in a comparison run. Error is set
// when Generate failed for this backend; ImagePath + Metadata are empty in
// that case.
type compareResult struct {
Backend string `json:"backend"`
ImagePath string `json:"image_path,omitempty"`
Seed int64 `json:"seed"`
LatencyMs int64 `json:"latency_ms,omitempty"`
Model string `json:"model,omitempty"`
VRAMUsedMiB int64 `json:"vram_used_mib,omitempty"`
Metadata map[string]any `json:"metadata,omitempty"`
Error string `json:"error,omitempty"`
}
func generateOne(ctx context.Context, cfg *config.Config, name, finalPrompt, negative string, w, h int, seed int64, steps int, runDir, rawPrompt string) (compareResult, error) {
be, err := buildBackend(cfg, name)
if err != nil {
return compareResult{Backend: name}, err
}
attachUsageSink(be)
req := backend.Request{
Prompt: finalPrompt,
NegativePrompt: negative,
Width: w,
Height: h,
Steps: steps,
Seed: seed,
}
res, err := be.Generate(ctx, req)
if err != nil {
return compareResult{Backend: name}, err
}
defer res.ImageReader.Close()
imgBytes, err := io.ReadAll(res.ImageReader)
if err != nil {
return compareResult{Backend: name}, fmt.Errorf("read image: %w", err)
}
imgPath := filepath.Join(runDir, output.Slug(rawPrompt)+"--"+output.Slug(name)+"."+extFromMime(res.MimeType))
if err := os.WriteFile(imgPath, imgBytes, 0o644); err != nil {
return compareResult{Backend: name}, fmt.Errorf("write %s: %w", imgPath, err)
}
cr := compareResult{
Backend: name,
ImagePath: imgPath,
Seed: seedFromMetadata(res.Metadata, seed),
LatencyMs: metaInt64(res.Metadata, "latency_ms"),
Model: metaString(res.Metadata, "model"),
Metadata: res.Metadata,
}
if v, ok := res.Metadata["vram_used_mib"].(int64); ok {
cr.VRAMUsedMiB = v
}
return cr, nil
}
func successfulResults(rs []compareResult) []compareResult {
out := make([]compareResult, 0, len(rs))
for _, r := range rs {
if r.Error == "" && r.ImagePath != "" {
out = append(out, r)
}
}
return out
}
func writeCompareSidecar(path, rawPrompt, style, negative string, w, h int, seed int64, steps int, results []compareResult) error {
body := map[string]any{
"timestamp": time.Now().UTC().Format(time.RFC3339),
"prompt": rawPrompt,
"style": style,
"negative": negative,
"width": w,
"height": h,
"seed": seed,
"steps": steps,
"results": results,
"backends": backendNames(results),
"successful": len(successfulResults(results)),
"total": len(results),
}
data, err := json.MarshalIndent(body, "", " ")
if err != nil {
return fmt.Errorf("marshal sidecar: %w", err)
}
return os.WriteFile(path, append(data, '\n'), 0o644)
}
func backendNames(rs []compareResult) []string {
out := make([]string, len(rs))
for i, r := range rs {
out[i] = r.Backend
}
sort.Strings(out)
return out
}
// writeContactSheet stitches a grid of (image, label) cells into one PNG.
// Cells are sized to fit in a target width of ~2400px while keeping each
// individual image full-resolution (no downscale) up to the column limit;
// past that, images sit at their native size and we just lay them out.
//
// The grid is a simple horizontal row when N <= 4; otherwise N/2 rows of 2.
// This is a contact sheet, not a fancy gallery — readability for side-by-
// side eyeballing is the goal.
func writeContactSheet(path, prompt string, results []compareResult) error {
if len(results) == 0 {
return fmt.Errorf("no successful results to lay out")
}
cells := make([]contactCell, 0, len(results))
for _, r := range results {
img, err := readPNG(r.ImagePath)
if err != nil {
return fmt.Errorf("read %s: %w", r.ImagePath, err)
}
cells = append(cells, contactCell{
Image: img,
Label: r.Backend,
SubLabel: fmt.Sprintf("%dms · seed %d", r.LatencyMs, r.Seed),
})
}
cols := len(cells)
if cols > 4 {
cols = 2
}
rows := (len(cells) + cols - 1) / cols
const labelH = 64
const pad = 16
cellW := cells[0].Image.Bounds().Dx()
cellH := cells[0].Image.Bounds().Dy()
for _, c := range cells {
if w := c.Image.Bounds().Dx(); w > cellW {
cellW = w
}
if h := c.Image.Bounds().Dy(); h > cellH {
cellH = h
}
}
totalW := cols*cellW + (cols+1)*pad
totalH := rows*(cellH+labelH) + (rows+1)*pad + 48 // header band
canvas := image.NewRGBA(image.Rect(0, 0, totalW, totalH))
draw.Draw(canvas, canvas.Bounds(), &image.Uniform{C: color.RGBA{R: 30, G: 30, B: 35, A: 255}}, image.Point{}, draw.Src)
// Header: show the truncated prompt.
headerText := "imagen compare — " + truncate(prompt, 100)
drawText(canvas, headerText, pad, 30, color.RGBA{R: 240, G: 240, B: 245, A: 255})
for i, c := range cells {
col := i % cols
row := i / cols
x0 := pad + col*(cellW+pad)
y0 := 48 + pad + row*(cellH+labelH+pad)
// Center the image inside the cell when smaller than the max cell size.
iw := c.Image.Bounds().Dx()
ih := c.Image.Bounds().Dy()
offX := (cellW - iw) / 2
offY := (cellH - ih) / 2
dstRect := image.Rect(x0+offX, y0+offY, x0+offX+iw, y0+offY+ih)
draw.Draw(canvas, dstRect, c.Image, c.Image.Bounds().Min, draw.Src)
// Label band underneath.
labelY := y0 + cellH + 20
drawText(canvas, c.Label, x0+8, labelY, color.RGBA{R: 250, G: 250, B: 250, A: 255})
drawText(canvas, c.SubLabel, x0+8, labelY+22, color.RGBA{R: 180, G: 180, B: 190, A: 255})
}
f, err := os.Create(path)
if err != nil {
return fmt.Errorf("create %s: %w", path, err)
}
defer f.Close()
return png.Encode(f, canvas)
}
type contactCell struct {
Image image.Image
Label string
SubLabel string
}
func readPNG(path string) (image.Image, error) {
f, err := os.Open(path)
if err != nil {
return nil, err
}
defer f.Close()
img, _, err := image.Decode(f)
return img, err
}
func drawText(dst *image.RGBA, s string, x, y int, c color.Color) {
drawer := &font.Drawer{
Dst: dst,
Src: &image.Uniform{C: c},
Face: basicfont.Face7x13,
Dot: fixed.Point26_6{X: fixed.I(x), Y: fixed.I(y)},
}
drawer.DrawString(s)
}
func truncate(s string, max int) string {
if len(s) <= max {
return s
}
return s[:max-1] + "…"
}
func splitCSV(s string) []string {
parts := strings.Split(s, ",")
out := make([]string, 0, len(parts))
for _, p := range parts {
p = strings.TrimSpace(p)
if p != "" {
out = append(out, p)
}
}
return out
}
func metaInt64(m map[string]any, key string) int64 {
v, ok := m[key]
if !ok {
return 0
}
switch n := v.(type) {
case int64:
return n
case int:
return int64(n)
case float64:
return int64(n)
}
return 0
}

203
cmd/imagen/compare_test.go Normal file
View File

@@ -0,0 +1,203 @@
package main
import (
"bytes"
"context"
"encoding/json"
"image/png"
"os"
"path/filepath"
"strings"
"testing"
)
// runCompareWithEnv runs the compare subcommand in a writable tmpdir, with
// XDG_CONFIG_HOME pointing somewhere empty so no host imagen.yaml leaks in.
func runCompareWithEnv(t *testing.T, args []string) (stderr, stdout *bytes.Buffer, runDir string, err error) {
t.Helper()
tmp := t.TempDir()
t.Setenv("XDG_CONFIG_HOME", filepath.Join(tmp, "no-config"))
t.Setenv("HOME", tmp)
out := filepath.Join(tmp, "compare")
// stdlib flag parsing requires flags after the leading positional. Append
// --output at the end so any caller-supplied flags still parse cleanly.
args = append(args, "--output", out)
// Capture stdout/stderr via os pipes since runCompare writes directly.
oldStdout := os.Stdout
oldStderr := os.Stderr
rOut, wOut, _ := os.Pipe()
rErr, wErr, _ := os.Pipe()
os.Stdout = wOut
os.Stderr = wErr
defer func() {
os.Stdout = oldStdout
os.Stderr = oldStderr
}()
cmdErr := runCompare(context.Background(), args)
_ = wOut.Close()
_ = wErr.Close()
stdout = &bytes.Buffer{}
stderr = &bytes.Buffer{}
_, _ = stdout.ReadFrom(rOut)
_, _ = stderr.ReadFrom(rErr)
entries, _ := os.ReadDir(out)
if len(entries) == 1 {
runDir = filepath.Join(out, entries[0].Name())
}
return stderr, stdout, runDir, cmdErr
}
func TestCompareHappyPathWithMockBackends(t *testing.T) {
// Two mock instances stand in for two different backends. mock ignores
// cfg so we can reuse the registered type as the instance name and skip
// writing imagen.yaml entirely.
stderr, stdout, runDir, err := runCompareWithEnv(t, []string{
"a cat in a fishbowl",
"--models", "mock,mock",
"--size", "64x64",
"--seed", "42",
})
if err != nil {
t.Fatalf("runCompare: %v\nstderr: %s", err, stderr.String())
}
if runDir == "" {
t.Fatal("expected a run directory under --output")
}
// Sidecar JSON
sidecar := filepath.Join(runDir, "compare.json")
data, err := os.ReadFile(sidecar)
if err != nil {
t.Fatalf("read sidecar: %v", err)
}
var body struct {
Prompt string `json:"prompt"`
Successful int `json:"successful"`
Total int `json:"total"`
Results []struct {
Backend string `json:"backend"`
ImagePath string `json:"image_path"`
Error string `json:"error"`
} `json:"results"`
}
if err := json.Unmarshal(data, &body); err != nil {
t.Fatalf("parse sidecar: %v\n%s", err, data)
}
if body.Prompt != "a cat in a fishbowl" {
t.Errorf("prompt = %q", body.Prompt)
}
if body.Total != 2 || body.Successful != 2 {
t.Errorf("counts = %d successful / %d total", body.Successful, body.Total)
}
for _, r := range body.Results {
if r.Error != "" {
t.Errorf("backend %s errored: %s", r.Backend, r.Error)
}
if _, err := os.Stat(r.ImagePath); err != nil {
t.Errorf("image not on disk for %s: %v", r.Backend, err)
}
}
// Contact sheet path was printed on stdout.
sheet := strings.TrimSpace(stdout.String())
if sheet == "" {
t.Fatal("expected contact sheet path on stdout")
}
f, err := os.Open(sheet)
if err != nil {
t.Fatalf("open contact sheet: %v", err)
}
defer f.Close()
img, err := png.Decode(f)
if err != nil {
t.Fatalf("decode contact sheet PNG: %v", err)
}
if w := img.Bounds().Dx(); w < 100 {
t.Errorf("contact sheet looks empty (width %d)", w)
}
}
func TestCompareSkipContactSheet(t *testing.T) {
stderr, stdout, runDir, err := runCompareWithEnv(t, []string{
"x",
"--models", "mock",
"--size", "32x32",
"--seed", "1",
"--no-contact-sheet",
})
if err != nil {
t.Fatalf("runCompare: %v\nstderr: %s", err, stderr.String())
}
if got := strings.TrimSpace(stdout.String()); got != "" {
t.Errorf("expected no stdout output (no contact sheet), got %q", got)
}
if _, err := os.Stat(filepath.Join(runDir, "contact-sheet.png")); err == nil {
t.Errorf("contact-sheet.png should not exist with --no-contact-sheet")
}
}
func TestCompareRecordsBackendErrors(t *testing.T) {
// One real (mock) + one unknown. Unknown should fail but not abort the
// run — sidecar records both, contact sheet built from successes only.
stderr, _, runDir, err := runCompareWithEnv(t, []string{
"y",
"--models", "mock,this-instance-does-not-exist",
"--size", "32x32",
})
if err != nil {
t.Fatalf("runCompare: %v\nstderr: %s", err, stderr.String())
}
sidecar := filepath.Join(runDir, "compare.json")
data, _ := os.ReadFile(sidecar)
var body struct {
Successful int `json:"successful"`
Total int `json:"total"`
Results []struct {
Backend string `json:"backend"`
Error string `json:"error"`
} `json:"results"`
}
if err := json.Unmarshal(data, &body); err != nil {
t.Fatalf("parse sidecar: %v", err)
}
if body.Total != 2 {
t.Errorf("expected 2 results, got %d", body.Total)
}
if body.Successful != 1 {
t.Errorf("expected 1 success, got %d", body.Successful)
}
var sawError bool
for _, r := range body.Results {
if r.Backend == "this-instance-does-not-exist" && r.Error != "" {
sawError = true
}
}
if !sawError {
t.Errorf("expected an error recorded for the unknown backend")
}
}
func TestCompareNoModelsFails(t *testing.T) {
_, _, _, err := runCompareWithEnv(t, []string{"x"})
if err == nil {
t.Fatal("expected error when --models is empty")
}
if !strings.Contains(err.Error(), "--models") {
t.Errorf("error should mention --models, got %v", err)
}
}
func TestCompareNoPromptFails(t *testing.T) {
_, _, _, err := runCompareWithEnv(t, []string{"--models", "mock"})
if err == nil {
t.Fatal("expected error when prompt is missing")
}
if !strings.Contains(err.Error(), "missing prompt") {
t.Errorf("error should mention missing prompt, got %v", err)
}
}

View File

@@ -18,6 +18,8 @@ const helpText = `imagen — model-agnostic image generation
Usage: Usage:
imagen generate <prompt> [flags] generate one image imagen generate <prompt> [flags] generate one image
imagen compare <prompt> --models a,b,c [flags]
run one prompt across N backends + contact sheet
imagen worker [flags] consume the imagen.jobs queue (daemon) imagen worker [flags] consume the imagen.jobs queue (daemon)
imagen backends list registered backend types imagen backends list registered backend types
imagen config init print a sample imagen.yaml on stdout imagen config init print a sample imagen.yaml on stdout
@@ -46,6 +48,8 @@ func main() {
switch os.Args[1] { switch os.Args[1] {
case "generate": case "generate":
err = runGenerate(ctx, args) err = runGenerate(ctx, args)
case "compare":
err = runCompare(ctx, args)
case "worker": case "worker":
err = runWorker(ctx, args) err = runWorker(ctx, args)
case "backends": case "backends":

310
docs/backends.md Normal file
View File

@@ -0,0 +1,310 @@
# ImaGen backends
This document covers the local-ComfyUI backend plug-in story: how adapters
are layered, how to add a new model without touching Go, and the per-model
setup steps for the bundled templates.
For the host-side ComfyUI install (mRock — venv, weights for the default
FLUX.1-schnell, systemd, VRAM coexistence with Ollama, smoke test against
the raw HTTP API), see [`setup-comfyui-mrock.md`](setup-comfyui-mrock.md).
## Architecture: Path 1 — workflow-template adapter
`imagen generate` and `imagen compare` dispatch through the `comfyui`
adapter, which holds the HTTP plumbing (`/prompt`, `/history/{id}`, `/view`,
`/system_stats`) and treats the workflow itself as data. Each backend
instance in `imagen.yaml` picks a workflow JSON via the `workflow:` key.
Adding a new model is yaml + JSON, never Go:
```
internal/backend/
comfyui.go # one adapter, all ComfyUI models
workflow_template.go # loader + token-substitution
workflows/
flux1-schnell.json # bundled templates (embedded with //go:embed)
flux2-klein.json
sd35-medium.json
```
### Why Path 1 over per-family adapters (`comfyui-flux.go`, `comfyui-sd3.go`…)
- **Workflow JSON is the natural exchange format**. ComfyUI users export
workflows from its GUI as JSON. Anything else means rebuilding the graph
by hand in Go for every new model.
- **Adding a model is a config change, not a build change**. With Path 2,
every new family is a Go file, a new test file, a registry entry, a new
worker binary, a redeploy. Path 1 lets us land a new model with one yaml
block + one JSON file + one section in this doc.
- **The HTTP plumbing is identical across families**. `/prompt`,
`/history`, `/view`, the retry policy, the "value not in list" hint, VRAM
reporting — none of it depends on the workflow shape. Path 2 would
duplicate that across files.
- **Failure isolation stays clean**. The workflow loader fails at adapter
construction (`imagen backends` surfaces the error), the HTTP layer
fails at `Generate`, and ComfyUI's own validation surfaces missing-model
hints. Each layer's error message points at the right config knob.
Path 2's argument was "each family owns its quirks (samplers, schedulers,
dual-stage etc.)". That argument doesn't survive contact with the
substitution-map design: per-family knobs are just key/value fields in the
yaml block and `${shift}`/`${guidance}`/`${cfg}` placeholders in the
template. No code duplication, no inheritance to debug.
### Token substitution
`workflow_template.SubstituteWorkflow` walks the parsed JSON and replaces
every whole-value string of the form `"${key}"` with the typed value from
the substitution map. Numbers stay numbers, strings stay strings — no
round-tripping through `strings.Replace`.
The substitution map is built per call from:
1. **Request fields** (always present): `${prompt}`, `${negative}`,
`${width}`, `${height}`, `${seed}`, `${steps}`, `${sampler}`,
`${scheduler}`, `${cfg}`.
2. **Every scalar field from the yaml block** (string / int / int64 /
float64 / bool), minus framework keys (`type`, `base_url`, `workflow`,
`default_*`). So `${vae}`, `${clip}`, `${clip_l}`, `${clip_t5}`,
`${dtype}`, `${shift}`, `${guidance}` all become substitutable just by
being in yaml.
3. **Sensible defaults** for the common optional knobs above, so a
workflow that references `${dtype}` without the user setting one in
yaml still substitutes cleanly (`fp8_e4m3fn` for FLUX, `3.0` for SD3
shift, etc.). Extra defaults are ignored by workflows that don't
reference them.
Partial matches (e.g. `"prefix ${prompt} suffix"`) are deliberately **not**
substituted — the placeholder must be the entire value so we can preserve
its JSON type. This prevents a prompt containing literal `${seed}` text
from corrupting the workflow.
Unknown placeholders (referenced in JSON but missing from the substitution
map) error out before the workflow leaves the binary.
### Back-compat
The `workflow:` field defaults to `flux1-schnell` if omitted. Existing
yaml blocks like the pre-#10 FLUX.1-schnell instance:
```yaml
flux-schnell-local:
type: comfyui
base_url: http://mrock:8188
model: flux1-schnell.safetensors
```
still work unchanged — they implicitly pick up the migrated
`flux1-schnell.json` template, which keeps the same node IDs (6, 8, 9, 10,
11, 12, 13, 27, 30, 31) as the historical hardcoded workflow.
## Bundled workflows
### FLUX.1-schnell — the back-compat default
| Field | Default | Notes |
|---|---|---|
| `model` | `flux1-schnell.safetensors` | drop in `models/unet/` |
| `vae` | `ae.safetensors` | `models/vae/` |
| `clip_l` | `clip_l.safetensors` | `models/clip/` |
| `clip_t5` | `t5xxl_fp8_e4m3fn.safetensors` | `models/clip/` |
| `dtype` | `fp8_e4m3fn` | weight dtype for the UNet loader |
| `default_steps` / `default_cfg` | 4 / 1.0 | schnell is distilled to ~4 steps |
VRAM peak ~1012 GB at 1024×1024. Install path:
[`setup-comfyui-mrock.md`](setup-comfyui-mrock.md). Already shipping.
### FLUX.2 [klein] 4B — direct upgrade
Released by Black Forest Labs late 2025 / early 2026, BFL non-commercial
license. The distilled 4B "klein" variant lands sub-second on the RTX
4070 Ti SUPER and shares the new Qwen-based text encoder + a re-trained
VAE with the larger family.
```yaml
flux2-klein-local:
type: comfyui
base_url: http://mrock:8188
workflow: flux2-klein
model: flux-2-klein-base-4b-fp8.safetensors # models/unet/
vae: flux2-vae.safetensors # models/vae/
clip: qwen_3_4b.safetensors # models/text_encoders/
dtype: fp8_e4m3fn
default_steps: 4
default_cfg: 1.0
guidance: 4.0
```
**Model downloads** (on mRock, ungated mirrors when available):
```bash
cd ~/dev/comfyui/models
curl -L -o unet/flux-2-klein-base-4b-fp8.safetensors \
https://huggingface.co/black-forest-labs/FLUX.2-klein/resolve/main/flux-2-klein-base-4b-fp8.safetensors
curl -L -o vae/flux2-vae.safetensors \
https://huggingface.co/black-forest-labs/FLUX.2-klein/resolve/main/flux2-vae.safetensors
mkdir -p text_encoders
curl -L -o text_encoders/qwen_3_4b.safetensors \
https://huggingface.co/black-forest-labs/FLUX.2-klein/resolve/main/qwen_3_4b.safetensors
```
BFL's primary repo is gated; if `curl` returns 401, configure an HF token
in `~/.cache/huggingface/token` or use one of the community mirrors
(check the official model card for the current list). The filenames the
template references match BFL's canonical names — rename downloads to
match if a mirror uses different ones.
VRAM peak: ~8.5 GB (4B fp8). With Ollama parked at ~8 GB this still fits;
unlike FLUX.1-schnell, klein doesn't require stopping Ollama on mRock.
### SD3.5-medium — single-checkpoint variant
Stability AI's 2.5B mid-size model with bundled text encoders. The
`incl_clips_t5xxlfp8scaled` variant ships clip_g + clip_l + t5xxl_fp8 all
in one `.safetensors`, so the workflow uses `CheckpointLoaderSimple`
instead of separate UNet/VAE/CLIP loaders.
```yaml
sd35-medium-local:
type: comfyui
base_url: http://mrock:8188
workflow: sd35-medium
model: sd3.5_medium_incl_clips_t5xxlfp8scaled.safetensors # models/checkpoints/
default_steps: 28
default_sampler: dpmpp_2m
default_scheduler: sgm_uniform
default_cfg: 4.5
shift: 3.0
```
**Model download** (on mRock):
```bash
cd ~/dev/comfyui/models
curl -L -o checkpoints/sd3.5_medium_incl_clips_t5xxlfp8scaled.safetensors \
https://huggingface.co/stabilityai/stable-diffusion-3.5-medium/resolve/main/sd3.5_medium_incl_clips_t5xxlfp8scaled.safetensors
```
VRAM peak: ~9.9 GB at 1024×1024. Same envelope as FLUX.1-schnell — stop
Ollama before generating, restart after.
## Adding a new bundled workflow
1. **Export from ComfyUI**: load the model in the ComfyUI GUI, build a
text-to-image workflow that produces what you want, "Save (API
Format)" — the file you get is the right shape.
2. **Sprinkle placeholders**: open the JSON and replace per-call values
with `${name}` tokens. Whole-value substitution only:
```json
"inputs": {
"text": "${prompt}", // was "a cat sitting on a chair"
"seed": "${seed}", // was 1234567
"steps": "${steps}", // was 28
"cfg": "${cfg}",
"sampler_name": "${sampler}",
"scheduler": "${scheduler}",
"width": "${width}",
"height": "${height}"
}
```
Use `${model}` for the checkpoint / unet filename and any per-template
knobs (`${vae}`, `${shift}`, `${guidance}`, `${clip}` …).
3. **Drop it into `internal/backend/workflows/<name>.json`**. The
`//go:embed workflows/*.json` directive in `workflow_template.go`
picks it up at build time — no registry entry needed.
4. **Add a yaml instance** in `internal/config/config.go`'s `Sample` block
for `imagen config init` (and `~/.config/imagen.yaml`) so users
discover the new backend.
5. **Document the model files + HF download URLs** in this doc.
6. **Smoke test**: `imagen generate "test" --backend <new-instance>
--size 1024x1024` should produce an image.
Per-call overrides for sampler/scheduler/cfg go via `--steps`, `--seed`,
and (programmatic) `backend.Request.BackendOpts["sampler"]` /
`["scheduler"]` / `["cfg"]`. The compare harness forwards the
constant-across-backends knobs verbatim.
## Loading a workflow from disk (one-off)
Pass an absolute filesystem path as `workflow:` and the adapter reads it
from disk instead of the embedded FS. Handy for prototyping a new model
before committing it:
```yaml
my-experimental:
type: comfyui
base_url: http://mrock:8188
workflow: /home/m/dev/comfyui/workflows/my-test.json
model: my-test-model.safetensors
```
The fallback chain is: filesystem path (if the string looks like a path
or ends in `.json`), then bundled lookup by name, then bundled lookup
with `.json` appended.
## `imagen compare`: cross-backend evaluation
```bash
imagen compare "a wizard casting a spell" \
--models flux-schnell-local,flux2-klein-local,sd35-medium-local \
--size 1024x1024 \
--output ~/Pictures/imagen/compare
```
Per run, `compare`:
- creates `<output>/<YYYYMMDD-HHMMSS>-<prompt-slug>/`
- dispatches each named backend sequentially (mRock has one GPU; parallel
would OOM) — one backend's failure doesn't abort the run
- writes per-backend PNGs as `<prompt-slug>--<backend-slug>.png`
- writes `compare.json` listing every attempt (success + failure) with
per-model `seed`, `latency_ms`, `model`, `vram_used_mib`, full
`metadata` map, and the error string for any failure
- composites a `contact-sheet.png` with the prompt as header and each
cell labelled `<backend>` / `<latency>ms · seed <n>`
Flags mirror `generate`: `--seed`, `--steps`, `--style`, `--negative`,
`--size` are shared across all backends. `--no-contact-sheet` skips the
composite when only the per-image PNGs and sidecar matter (e.g. for a
worker script that builds its own diff view).
## Diagnostics
`imagen backends` shows every instance with its registration state. For
local ComfyUI, the status is currently just `registered` (we don't probe
the upstream HTTP endpoint at startup — the boot-helper hint kicks in on
first generation if mRock is asleep).
Per-backend errors emit at most three kinds:
1. **Adapter construction failure** (e.g. workflow JSON not found,
missing required yaml field). Caught at `buildBackend` time:
`imagen: backend "<name>": <err>`.
2. **HTTP / runtime failure during Generate**. Wrapped with the boot
helper for `connection refused`/`no such host`/timeouts pointing at
`boot-whitetower mrock` so a sleeping mRock has an obvious next step.
3. **ComfyUI workflow-validation failure** (200-with-node_errors or 400).
Surfaces with a model-not-found hint (matching `value_not_in_list` +
`unet_name`/`ckpt_name`) when applicable, pointing back at this doc.
## Worker daemon notes
`imagen worker` (the `imagen.jobs` queue consumer) uses the same adapter
+ workflow lookup as the synchronous CLI — flexsiebels' `/imagine` UI
INSERTs a `backend = <instance>` row, the worker claims it, and the
underlying ComfyUI HTTP calls are identical to what `generate` makes. No
worker-specific changes are required when a new backend lands; the
config + workflow are the only state that has to be present on the
worker host.
After merging a new template or yaml block:
```bash
# On the worker host (mRiver today):
systemctl --user restart imagen-worker
```
The daemon-rebuild trap from issue #9 still applies: if you build the
imagen binary on the dev machine and `scp` it over, restart the unit so
systemd picks up the new ELF.

View File

@@ -4,14 +4,21 @@
``` ```
imagen generate <prompt> [flags] generate one image imagen generate <prompt> [flags] generate one image
imagen compare <prompt> --models a,b,c [flags]
run one prompt across N backends + contact sheet
imagen worker [flags] consume the imagen.jobs queue (daemon)
imagen backends list configured + registered backends imagen backends list configured + registered backends
imagen config init print a sample imagen.yaml on stdout imagen config init print a sample imagen.yaml on stdout
imagen config validate parse + validate the active config imagen config validate parse + validate the active config
imagen config path print the resolved config path imagen config path print the resolved config path
imagen serve [--addr :8080] (stub) start the HTTP server imagen serve [--addr :8080] (stub) start the HTTP server
imagen usage [--since DATE] show cost-tracking rows
imagen version print version imagen version print version
``` ```
For the per-backend setup (FLUX.1, FLUX.2 [klein], SD3.5 medium, …) and
the architecture rationale, see [`backends.md`](backends.md).
## `generate` flags ## `generate` flags
| Flag | Default | Notes | | Flag | Default | Notes |

3
go.mod
View File

@@ -4,6 +4,7 @@ go 1.25.0
require ( require (
github.com/jackc/pgx/v5 v5.9.2 github.com/jackc/pgx/v5 v5.9.2
golang.org/x/image v0.40.0
gopkg.in/yaml.v3 v3.0.1 gopkg.in/yaml.v3 v3.0.1
) )
@@ -12,5 +13,5 @@ require (
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
github.com/kr/text v0.2.0 // indirect github.com/kr/text v0.2.0 // indirect
github.com/rogpeppe/go-internal v1.14.1 // indirect github.com/rogpeppe/go-internal v1.14.1 // indirect
golang.org/x/text v0.29.0 // indirect golang.org/x/text v0.37.0 // indirect
) )

10
go.sum
View File

@@ -23,10 +23,12 @@ github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UV
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U= github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U= github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
golang.org/x/sync v0.17.0 h1:l60nONMj9l5drqw6jlhIELNv9I0A4OFgRsG9k2oT9Ug= golang.org/x/image v0.40.0 h1:Tw4GyDXMo+daZN1znreBRC3VayR1aLFUyUEOLUdW1a8=
golang.org/x/sync v0.17.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI= golang.org/x/image v0.40.0/go.mod h1:uIc348UZMSvS5Z65CVZ7iDPaNobNFEPeJ4kbqTOszmA=
golang.org/x/text v0.29.0 h1:1neNs90w9YzJ9BocxfsQNHKuAT4pkghyXc4nhZ6sJvk= golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=
golang.org/x/text v0.29.0/go.mod h1:7MhJOA9CD2qZyOKYazxdYMF85OwPdEr9jTtBpO7ydH4= golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
golang.org/x/text v0.37.0 h1:Cqjiwd9eSg8e0QAkyCaQTNHFIIzWtidPahFWR83rTrc=
golang.org/x/text v0.37.0/go.mod h1:a5sjxXGs9hsn/AJVwuElvCAo9v8QYLzvavO5z2PiM38=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q= gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=

View File

@@ -20,8 +20,9 @@ import (
const ComfyType = "comfyui" const ComfyType = "comfyui"
// Comfy is the ComfyUI adapter. It speaks the public `/prompt` + `/history` // Comfy is the ComfyUI adapter. It speaks the public `/prompt` + `/history`
// + `/view` HTTP API and submits a fixed FLUX.1 schnell workflow built from // + `/view` HTTP API and submits a workflow built by substituting Request
// the values in Request. // values into a JSON template (bundled under internal/backend/workflows/ or
// loaded from a filesystem path).
// //
// Concurrency: a single Comfy is safe to share across goroutines as long as // Concurrency: a single Comfy is safe to share across goroutines as long as
// the underlying http.Client is. Generate does not hold long-lived state. // the underlying http.Client is. Generate does not hold long-lived state.
@@ -29,15 +30,19 @@ type Comfy struct {
instance string instance string
base string base string
model string workflow string
vae string
clipL string // rawCfg keeps the original yaml block (minus framework keys) so we can
clipT5 string // expose every user-defined string/number as a workflow substitution
dtype string // without enumerating each per-model knob in Go. Empty values still get
// a substitution entry so a template can reference ${negative} when the
// request didn't pass one.
rawCfg map[string]any
defaultSteps int defaultSteps int
defaultSampler string defaultSampler string
defaultScheduler string defaultScheduler string
defaultCFG float64
httpClient *http.Client httpClient *http.Client
pollInterval time.Duration pollInterval time.Duration
@@ -49,12 +54,20 @@ type Comfy struct {
} }
// NewComfy is the registry constructor. cfg is the adapter's slice of // NewComfy is the registry constructor. cfg is the adapter's slice of
// imagen.yaml. Required keys: base_url, model. The rest have sensible FLUX // imagen.yaml.
// schnell defaults. //
// Required keys: base_url, model.
// Optional keys: workflow (defaults to "flux1-schnell" for back-compat with
// existing configs), default_steps, default_sampler, default_scheduler,
// default_cfg, plus any template-specific knobs (vae, clip, clip_l,
// clip_t5, dtype, shift, guidance, …) the chosen workflow references.
func NewComfy(name string, cfg map[string]any) (Backend, error) { func NewComfy(name string, cfg map[string]any) (Backend, error) {
if name == "" { if name == "" {
return nil, fmt.Errorf("comfyui: empty instance name") return nil, fmt.Errorf("comfyui: empty instance name")
} }
if cfg == nil {
cfg = map[string]any{}
}
base := strings.TrimRight(getString(cfg, "base_url", ""), "/") base := strings.TrimRight(getString(cfg, "base_url", ""), "/")
if base == "" { if base == "" {
return nil, fmt.Errorf("comfyui[%s]: base_url is required", name) return nil, fmt.Errorf("comfyui[%s]: base_url is required", name)
@@ -67,23 +80,27 @@ func NewComfy(name string, cfg map[string]any) (Backend, error) {
return nil, fmt.Errorf("comfyui[%s]: model is required", name) return nil, fmt.Errorf("comfyui[%s]: model is required", name)
} }
workflow := getString(cfg, "workflow", "flux1-schnell")
// Fail fast on a bad workflow ref so users see the error at startup,
// not on first /prompt submission.
if _, err := LoadWorkflowTemplate(workflow); err != nil {
return nil, fmt.Errorf("comfyui[%s]: %w", name, err)
}
c := &Comfy{ c := &Comfy{
instance: name, instance: name,
base: base, base: base,
model: model, workflow: workflow,
rawCfg: cfg,
vae: getString(cfg, "vae", "ae.safetensors"),
clipL: getString(cfg, "clip_l", "clip_l.safetensors"),
clipT5: getString(cfg, "clip_t5", "t5xxl_fp8_e4m3fn.safetensors"),
dtype: getString(cfg, "weight_dtype", "fp8_e4m3fn"),
defaultSteps: getInt(cfg, "default_steps", 4), defaultSteps: getInt(cfg, "default_steps", 4),
defaultSampler: getString(cfg, "default_sampler", "euler"), defaultSampler: getString(cfg, "default_sampler", "euler"),
defaultScheduler: getString(cfg, "default_scheduler", "simple"), defaultScheduler: getString(cfg, "default_scheduler", "simple"),
defaultCFG: getFloat(cfg, "default_cfg", 1.0),
httpClient: &http.Client{Timeout: 60 * time.Second}, httpClient: &http.Client{Timeout: 60 * time.Second},
pollInterval: 250 * time.Millisecond, pollInterval: 250 * time.Millisecond,
pollTimeout: 120 * time.Second, pollTimeout: 300 * time.Second,
randSeed: cryptoSeed, randSeed: cryptoSeed,
clientIDFn: randClientID, clientIDFn: randClientID,
@@ -103,19 +120,26 @@ func (c *Comfy) Generate(ctx context.Context, req Request) (*Result, error) {
sampler := c.defaultSampler sampler := c.defaultSampler
scheduler := c.defaultScheduler scheduler := c.defaultScheduler
cfg := c.defaultCFG
if v, ok := req.BackendOpts["sampler"].(string); ok && v != "" { if v, ok := req.BackendOpts["sampler"].(string); ok && v != "" {
sampler = v sampler = v
} }
if v, ok := req.BackendOpts["scheduler"].(string); ok && v != "" { if v, ok := req.BackendOpts["scheduler"].(string); ok && v != "" {
scheduler = v scheduler = v
} }
if v, ok := req.BackendOpts["cfg"].(float64); ok && v > 0 {
cfg = v
}
seed := req.Seed seed := req.Seed
if seed == 0 { if seed == 0 {
seed = c.randSeed() seed = c.randSeed()
} }
workflow := c.buildWorkflow(req.Prompt, req.NegativePrompt, width, height, seed, steps, sampler, scheduler) workflow, err := c.buildWorkflow(req.Prompt, req.NegativePrompt, width, height, seed, steps, sampler, scheduler, cfg)
if err != nil {
return nil, fmt.Errorf("comfyui[%s]: build workflow: %w", c.instance, err)
}
clientID := c.clientIDFn() clientID := c.clientIDFn()
start := time.Now() start := time.Now()
@@ -133,14 +157,17 @@ func (c *Comfy) Generate(ctx context.Context, req Request) (*Result, error) {
} }
latencyMs := time.Since(start).Milliseconds() latencyMs := time.Since(start).Milliseconds()
model := getString(c.rawCfg, "model", "")
meta := map[string]any{ meta := map[string]any{
"backend": c.instance, "backend": c.instance,
"backend_type": ComfyType, "backend_type": ComfyType,
"model": c.model, "workflow": c.workflow,
"model": model,
"seed": seed, "seed": seed,
"steps": steps, "steps": steps,
"sampler": sampler, "sampler": sampler,
"scheduler": scheduler, "scheduler": scheduler,
"cfg": cfg,
"width": width, "width": width,
"height": height, "height": height,
"latency_ms": latencyMs, "latency_ms": latencyMs,
@@ -173,6 +200,7 @@ func (c *Comfy) submitPrompt(ctx context.Context, workflow map[string]any, clien
return "", fmt.Errorf("comfyui: marshal workflow: %w", err) return "", fmt.Errorf("comfyui: marshal workflow: %w", err)
} }
model := getString(c.rawCfg, "model", "")
var lastErr error var lastErr error
for attempt := range 2 { for attempt := range 2 {
if attempt > 0 { if attempt > 0 {
@@ -196,7 +224,7 @@ func (c *Comfy) submitPrompt(ctx context.Context, workflow map[string]any, clien
_ = resp.Body.Close() _ = resp.Body.Close()
switch { switch {
case resp.StatusCode >= 200 && resp.StatusCode < 300: case resp.StatusCode >= 200 && resp.StatusCode < 300:
return parsePromptID(respBody, c.model) return parsePromptID(respBody, model)
case resp.StatusCode >= 500: case resp.StatusCode >= 500:
lastErr = fmt.Errorf("comfyui /prompt %d: %s", resp.StatusCode, snip(respBody)) lastErr = fmt.Errorf("comfyui /prompt %d: %s", resp.StatusCode, snip(respBody))
continue continue
@@ -333,98 +361,74 @@ func (c *Comfy) connError(err error) error {
// workflow-validation failures and put the diagnostics in node_errors; older // workflow-validation failures and put the diagnostics in node_errors; older
// builds use 200 + node_errors. This handles the 4xx flavour. // builds use 200 + node_errors. This handles the 4xx flavour.
func (c *Comfy) classifyBadRequest(status int, body []byte) error { func (c *Comfy) classifyBadRequest(status int, body []byte) error {
if hint, ok := missingModelHint(body, c.model); ok { model := getString(c.rawCfg, "model", "")
return fmt.Errorf("comfyui /prompt %d: %s — see docs/setup-comfyui-mrock.md", status, hint) if hint, ok := missingModelHint(body, model); ok {
return fmt.Errorf("comfyui /prompt %d: %s — see docs/backends.md", status, hint)
} }
return fmt.Errorf("comfyui /prompt %d: %s", status, snip(body)) return fmt.Errorf("comfyui /prompt %d: %s", status, snip(body))
} }
// buildWorkflow assembles the canonical FLUX.1 schnell ComfyUI workflow, // buildWorkflow loads the configured workflow template and substitutes the
// node-IDs matching the upstream "flux-schnell" template so anyone debugging // per-call placeholders (prompt, seed, sampler, …) plus any string/number
// in the ComfyUI UI sees a familiar shape. // fields the user defined in the yaml block. The set of placeholder keys
func (c *Comfy) buildWorkflow(prompt, negative string, w, h int, seed int64, steps int, sampler, scheduler string) map[string]any { // that aren't in `subs` produces an error from SubstituteWorkflow.
return map[string]any{ func (c *Comfy) buildWorkflow(prompt, negative string, w, h int, seed int64, steps int, sampler, scheduler string, cfg float64) (map[string]any, error) {
"6": map[string]any{ wf, err := LoadWorkflowTemplate(c.workflow)
"class_type": "CLIPTextEncode", if err != nil {
"inputs": map[string]any{ return nil, err
"text": prompt, }
"clip": []any{"11", 0}, subs := map[string]any{
}, "prompt": prompt,
}, "negative": negative,
"8": map[string]any{
"class_type": "VAEDecode",
"inputs": map[string]any{
"samples": []any{"31", 0},
"vae": []any{"10", 0},
},
},
"9": map[string]any{
"class_type": "SaveImage",
"inputs": map[string]any{
"filename_prefix": "imagen",
"images": []any{"8", 0},
},
},
"10": map[string]any{
"class_type": "VAELoader",
"inputs": map[string]any{"vae_name": c.vae},
},
"11": map[string]any{
"class_type": "DualCLIPLoader",
"inputs": map[string]any{
"clip_name1": c.clipT5,
"clip_name2": c.clipL,
"type": "flux",
},
},
"12": map[string]any{
"class_type": "UNETLoader",
"inputs": map[string]any{
"unet_name": c.model,
"weight_dtype": c.dtype,
},
},
"13": map[string]any{
"class_type": "CLIPTextEncode",
"inputs": map[string]any{
"text": negative,
"clip": []any{"11", 0},
},
},
"27": map[string]any{
"class_type": "EmptySD3LatentImage",
"inputs": map[string]any{
"width": w, "width": w,
"height": h, "height": h,
"batch_size": 1,
},
},
"30": map[string]any{
"class_type": "ModelSamplingFlux",
"inputs": map[string]any{
"model": []any{"12", 0},
"max_shift": 1.15,
"base_shift": 0.5,
"width": w,
"height": h,
},
},
"31": map[string]any{
"class_type": "KSampler",
"inputs": map[string]any{
"model": []any{"30", 0},
"seed": seed, "seed": seed,
"steps": steps, "steps": steps,
"cfg": 1.0, "sampler": sampler,
"sampler_name": sampler,
"scheduler": scheduler, "scheduler": scheduler,
"denoise": 1.0, "cfg": cfg,
"positive": []any{"6", 0},
"negative": []any{"13", 0},
"latent_image": []any{"27", 0},
},
},
} }
// Surface every scalar field from the yaml block so per-template knobs
// (vae, clip, clip_l, clip_t5, dtype, shift, guidance, …) work without
// adapter-code changes. Framework keys are excluded.
for k, v := range c.rawCfg {
switch k {
case "type", "base_url", "workflow",
"default_steps", "default_sampler", "default_scheduler", "default_cfg":
continue
}
if _, alreadySet := subs[k]; alreadySet {
// A per-call var (e.g. ${prompt}) beats anything yaml put under
// the same key — yaml can't shadow request-derived values.
continue
}
switch v := v.(type) {
case string, int, int64, float64, bool:
subs[k] = v
}
}
// Provide sensible defaults for common optional knobs so a workflow that
// references one of these doesn't fail substitution when the user
// didn't override it in yaml. Extra keys are ignored if the workflow
// doesn't reference them, so it's safe to always set the lot.
defaults := map[string]any{
"vae": "ae.safetensors",
"clip_l": "clip_l.safetensors",
"clip_t5": "t5xxl_fp8_e4m3fn.safetensors",
"clip": "qwen_3_4b.safetensors",
"dtype": "fp8_e4m3fn",
"guidance": 4.0,
"shift": 3.0,
}
for k, v := range defaults {
if _, ok := subs[k]; !ok {
subs[k] = v
}
}
if _, err := SubstituteWorkflow(wf, subs); err != nil {
return nil, err
}
return wf, nil
} }
// parsePromptID handles the 2xx /prompt response. ComfyUI sometimes 200s a // parsePromptID handles the 2xx /prompt response. ComfyUI sometimes 200s a
@@ -441,7 +445,7 @@ func parsePromptID(body []byte, model string) (string, error) {
} }
if len(resp.NodeErrors) > 0 || len(resp.Error) > 0 { if len(resp.NodeErrors) > 0 || len(resp.Error) > 0 {
if hint, ok := missingModelHint(body, model); ok { if hint, ok := missingModelHint(body, model); ok {
return "", fmt.Errorf("comfyui /prompt: %s — see docs/setup-comfyui-mrock.md", hint) return "", fmt.Errorf("comfyui /prompt: %s — see docs/backends.md", hint)
} }
return "", fmt.Errorf("comfyui /prompt rejected workflow: %s", snip(body)) return "", fmt.Errorf("comfyui /prompt rejected workflow: %s", snip(body))
} }
@@ -489,15 +493,21 @@ func parseHistory(body []byte, promptID string) (string, bool, error) {
} }
// missingModelHint returns a user-actionable message when the response body // missingModelHint returns a user-actionable message when the response body
// indicates the configured unet model isn't loaded on the server. ComfyUI // indicates the configured unet/checkpoint model isn't loaded on the server.
// uses both the human-readable "Value not in list" message and the enum // ComfyUI uses both the human-readable "Value not in list" message and the
// "value_not_in_list" type — match either. // enum "value_not_in_list" type — match either.
func missingModelHint(body []byte, model string) (string, bool) { func missingModelHint(body []byte, model string) (string, bool) {
s := string(body) s := string(body)
hasMarker := strings.Contains(s, "Value not in list") || strings.Contains(s, "value_not_in_list") hasMarker := strings.Contains(s, "Value not in list") || strings.Contains(s, "value_not_in_list")
if hasMarker && strings.Contains(s, "unet_name") { if !hasMarker {
return "", false
}
if strings.Contains(s, "unet_name") {
return fmt.Sprintf("model %q not present in the ComfyUI server's models/unet/", model), true return fmt.Sprintf("model %q not present in the ComfyUI server's models/unet/", model), true
} }
if strings.Contains(s, "ckpt_name") {
return fmt.Sprintf("checkpoint %q not present in the ComfyUI server's models/checkpoints/", model), true
}
return "", false return "", false
} }
@@ -536,6 +546,22 @@ func getInt(m map[string]any, k string, def int) int {
return def return def
} }
func getFloat(m map[string]any, k string, def float64) float64 {
if v, ok := m[k]; ok {
switch n := v.(type) {
case float64:
return n
case float32:
return float64(n)
case int:
return float64(n)
case int64:
return float64(n)
}
}
return def
}
func orDefaultInt(v, def int) int { func orDefaultInt(v, def int) int {
if v == 0 { if v == 0 {
return def return def

View File

@@ -312,7 +312,7 @@ func TestComfyMissingModelHintsAtSetupDoc(t *testing.T) {
t.Fatal("expected error") t.Fatal("expected error")
} }
msg := err.Error() msg := err.Error()
if !strings.Contains(msg, "docs/setup-comfyui-mrock.md") { if !strings.Contains(msg, "docs/backends.md") {
t.Errorf("error should point at the setup doc, got %v", err) t.Errorf("error should point at the setup doc, got %v", err)
} }
if !strings.Contains(msg, "flux1-schnell.safetensors") { if !strings.Contains(msg, "flux1-schnell.safetensors") {
@@ -331,7 +331,7 @@ func TestComfyMissingModelOn200WithNodeErrors(t *testing.T) {
if err == nil { if err == nil {
t.Fatal("expected error for node_errors on 200") t.Fatal("expected error for node_errors on 200")
} }
if !strings.Contains(err.Error(), "docs/setup-comfyui-mrock.md") { if !strings.Contains(err.Error(), "docs/backends.md") {
t.Errorf("error should point at the setup doc, got %v", err) t.Errorf("error should point at the setup doc, got %v", err)
} }
} }

View File

@@ -0,0 +1,156 @@
package backend
import (
"embed"
"encoding/json"
"fmt"
"io/fs"
"maps"
"os"
"path/filepath"
"regexp"
"sort"
"strings"
)
//go:embed workflows/*.json
var bundledWorkflows embed.FS
// placeholderRE matches a single-token placeholder like "${prompt}" — the
// whole string value must be the placeholder, leading/trailing whitespace
// allowed. This lets us preserve types (a numeric substitution becomes a
// JSON number, not a stringified one) instead of round-tripping through
// strings.Replace which would force everything into a string.
var placeholderRE = regexp.MustCompile(`^\s*\$\{([a-zA-Z][a-zA-Z0-9_]*)\}\s*$`)
// LoadWorkflowTemplate returns the parsed JSON for a workflow template.
// `name` is resolved in this order:
//
// 1. exact filesystem path that exists on disk (absolute or relative);
// 2. one of the bundled templates under internal/backend/workflows/
// (with or without the .json suffix).
//
// The returned map is a fresh deep copy of the template; callers can mutate
// it freely.
func LoadWorkflowTemplate(name string) (map[string]any, error) {
if name == "" {
return nil, fmt.Errorf("workflow template name is empty")
}
raw, err := readWorkflowBytes(name)
if err != nil {
return nil, err
}
var wf map[string]any
if err := json.Unmarshal(raw, &wf); err != nil {
return nil, fmt.Errorf("workflow %s: parse: %w", name, err)
}
return wf, nil
}
// BundledWorkflowNames returns the names of templates compiled into the
// binary, sorted. Each name is the basename without the .json suffix.
func BundledWorkflowNames() []string {
entries, err := fs.ReadDir(bundledWorkflows, "workflows")
if err != nil {
return nil
}
out := make([]string, 0, len(entries))
for _, e := range entries {
n := e.Name()
if !strings.HasSuffix(n, ".json") {
continue
}
out = append(out, strings.TrimSuffix(n, ".json"))
}
sort.Strings(out)
return out
}
func readWorkflowBytes(name string) ([]byte, error) {
// Filesystem path wins if it points at a real file. Lets a user override
// a bundled template by passing an absolute path in yaml.
if strings.ContainsRune(name, os.PathSeparator) || strings.HasSuffix(name, ".json") {
if b, err := os.ReadFile(name); err == nil {
return b, nil
} else if !os.IsNotExist(err) {
return nil, fmt.Errorf("workflow %s: %w", name, err)
}
}
// Bundled lookup. Try the literal name as a file inside workflows/, then
// with the .json suffix appended.
candidates := []string{
filepath.Join("workflows", name),
filepath.Join("workflows", name+".json"),
}
for _, c := range candidates {
if b, err := bundledWorkflows.ReadFile(c); err == nil {
return b, nil
}
}
return nil, fmt.Errorf("workflow %q not found (bundled templates: %v)", name, BundledWorkflowNames())
}
// SubstituteWorkflow walks wf and replaces every "${key}" string with the
// matching value from subs, preserving JSON types. Returns the set of
// placeholder keys it actually touched, so the caller can detect missing
// substitutions even when a key is defined in subs but never referenced in
// the workflow (typical when a yaml block sets a knob a different template
// would consume).
//
// Unknown placeholders (referenced in the workflow but absent from subs)
// produce an error so we never submit a workflow with raw "${foo}" tokens.
func SubstituteWorkflow(wf map[string]any, subs map[string]any) (used map[string]struct{}, err error) {
used = make(map[string]struct{})
walked, err := substituteValue(wf, subs, used)
if err != nil {
return nil, err
}
// substituteValue returns the replacement for the top-level value, which
// should still be the same map (just with mutated children).
if m, ok := walked.(map[string]any); ok {
// Copy back into wf so the caller's reference reflects the result.
for k := range wf {
delete(wf, k)
}
maps.Copy(wf, m)
}
return used, nil
}
func substituteValue(v any, subs map[string]any, used map[string]struct{}) (any, error) {
switch x := v.(type) {
case map[string]any:
out := make(map[string]any, len(x))
for k, child := range x {
replaced, err := substituteValue(child, subs, used)
if err != nil {
return nil, err
}
out[k] = replaced
}
return out, nil
case []any:
out := make([]any, len(x))
for i, child := range x {
replaced, err := substituteValue(child, subs, used)
if err != nil {
return nil, err
}
out[i] = replaced
}
return out, nil
case string:
if m := placeholderRE.FindStringSubmatch(x); m != nil {
key := m[1]
val, ok := subs[key]
if !ok {
return nil, fmt.Errorf("workflow placeholder ${%s} has no substitution", key)
}
used[key] = struct{}{}
return val, nil
}
return x, nil
default:
return v, nil
}
}

View File

@@ -0,0 +1,153 @@
package backend
import (
"os"
"path/filepath"
"slices"
"strings"
"testing"
)
func TestBundledWorkflowsParseable(t *testing.T) {
names := BundledWorkflowNames()
if len(names) == 0 {
t.Fatal("expected at least one bundled workflow")
}
mustHave := []string{"flux1-schnell", "flux2-klein", "sd35-medium"}
for _, want := range mustHave {
if !slices.Contains(names, want) {
t.Errorf("bundled workflows missing %q (have: %v)", want, names)
}
}
// Every bundled template must parse and contain at least one node.
for _, n := range names {
wf, err := LoadWorkflowTemplate(n)
if err != nil {
t.Errorf("LoadWorkflowTemplate(%q): %v", n, err)
continue
}
if len(wf) == 0 {
t.Errorf("workflow %q has zero nodes", n)
}
}
}
func TestLoadWorkflowFromFilesystem(t *testing.T) {
dir := t.TempDir()
path := filepath.Join(dir, "custom.json")
body := `{"1":{"class_type":"X","inputs":{"v":"${prompt}"}}}`
if err := os.WriteFile(path, []byte(body), 0o644); err != nil {
t.Fatalf("write tmp workflow: %v", err)
}
wf, err := LoadWorkflowTemplate(path)
if err != nil {
t.Fatalf("load from path: %v", err)
}
if _, ok := wf["1"]; !ok {
t.Errorf("custom workflow missing node 1")
}
}
func TestLoadWorkflowUnknownNameErrors(t *testing.T) {
_, err := LoadWorkflowTemplate("definitely-not-a-real-workflow")
if err == nil {
t.Fatal("expected error for unknown workflow name")
}
if !strings.Contains(err.Error(), "not found") {
t.Errorf("error should say not found, got %v", err)
}
}
func TestSubstituteWorkflowPreservesTypes(t *testing.T) {
wf := map[string]any{
"31": map[string]any{
"class_type": "KSampler",
"inputs": map[string]any{
"seed": "${seed}",
"steps": "${steps}",
"text": "${prompt}",
"cfg": "${cfg}",
},
},
}
subs := map[string]any{
"seed": int64(42),
"steps": 11,
"prompt": "a cat",
"cfg": 4.5,
}
used, err := SubstituteWorkflow(wf, subs)
if err != nil {
t.Fatalf("Substitute: %v", err)
}
if len(used) != 4 {
t.Errorf("used = %v, want all four", used)
}
inputs := wf["31"].(map[string]any)["inputs"].(map[string]any)
if seed, ok := inputs["seed"].(int64); !ok || seed != 42 {
t.Errorf("seed = %T %v, want int64 42", inputs["seed"], inputs["seed"])
}
if steps, ok := inputs["steps"].(int); !ok || steps != 11 {
t.Errorf("steps = %T %v, want int 11", inputs["steps"], inputs["steps"])
}
if text, ok := inputs["text"].(string); !ok || text != "a cat" {
t.Errorf("text = %T %v, want string", inputs["text"], inputs["text"])
}
if cfg, ok := inputs["cfg"].(float64); !ok || cfg != 4.5 {
t.Errorf("cfg = %T %v, want float64 4.5", inputs["cfg"], inputs["cfg"])
}
}
func TestSubstituteWorkflowMissingPlaceholderErrors(t *testing.T) {
wf := map[string]any{
"1": map[string]any{"inputs": map[string]any{"v": "${missing}"}},
}
_, err := SubstituteWorkflow(wf, map[string]any{})
if err == nil {
t.Fatal("expected error for missing placeholder")
}
if !strings.Contains(err.Error(), "${missing}") {
t.Errorf("error should name the placeholder, got %v", err)
}
}
func TestSubstituteWorkflowOnlyWholeTokens(t *testing.T) {
// Partial-match strings ("prefix ${prompt} suffix") are NOT substituted —
// the placeholder must be the whole value so we can preserve types.
wf := map[string]any{
"1": map[string]any{"inputs": map[string]any{
"keep_string": "stuff with ${prompt} inside",
"replace_full": "${prompt}",
}},
}
used, err := SubstituteWorkflow(wf, map[string]any{"prompt": "x"})
if err != nil {
t.Fatalf("Substitute: %v", err)
}
inputs := wf["1"].(map[string]any)["inputs"].(map[string]any)
if inputs["keep_string"].(string) != "stuff with ${prompt} inside" {
t.Errorf("partial match should be left alone, got %q", inputs["keep_string"])
}
if inputs["replace_full"].(string) != "x" {
t.Errorf("full-value match should substitute, got %q", inputs["replace_full"])
}
if _, ok := used["prompt"]; !ok {
t.Errorf("used should track keys that fired")
}
}
func TestFlux1SchnellTemplateMatchesLegacyShape(t *testing.T) {
// Regression guard against the historical hardcoded workflow: every
// node ID the old Comfy.buildWorkflow used must still exist in the
// migrated template.
wf, err := LoadWorkflowTemplate("flux1-schnell")
if err != nil {
t.Fatalf("load flux1-schnell: %v", err)
}
legacyNodes := []string{"6", "8", "9", "10", "11", "12", "13", "27", "30", "31"}
for _, id := range legacyNodes {
if _, ok := wf[id]; !ok {
t.Errorf("flux1-schnell template missing node %q (legacy parity)", id)
}
}
}

View File

@@ -0,0 +1,84 @@
{
"6": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "${prompt}",
"clip": ["11", 0]
}
},
"8": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["31", 0],
"vae": ["10", 0]
}
},
"9": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "imagen",
"images": ["8", 0]
}
},
"10": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "${vae}"
}
},
"11": {
"class_type": "DualCLIPLoader",
"inputs": {
"clip_name1": "${clip_t5}",
"clip_name2": "${clip_l}",
"type": "flux"
}
},
"12": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "${model}",
"weight_dtype": "${dtype}"
}
},
"13": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "${negative}",
"clip": ["11", 0]
}
},
"27": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": "${width}",
"height": "${height}",
"batch_size": 1
}
},
"30": {
"class_type": "ModelSamplingFlux",
"inputs": {
"model": ["12", 0],
"max_shift": 1.15,
"base_shift": 0.5,
"width": "${width}",
"height": "${height}"
}
},
"31": {
"class_type": "KSampler",
"inputs": {
"model": ["30", 0],
"seed": "${seed}",
"steps": "${steps}",
"cfg": "${cfg}",
"sampler_name": "${sampler}",
"scheduler": "${scheduler}",
"denoise": 1.0,
"positive": ["6", 0],
"negative": ["13", 0],
"latent_image": ["27", 0]
}
}
}

View File

@@ -0,0 +1,79 @@
{
"6": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "${prompt}",
"clip": ["11", 0]
}
},
"8": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["31", 0],
"vae": ["10", 0]
}
},
"9": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "imagen",
"images": ["8", 0]
}
},
"10": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "${vae}"
}
},
"11": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "${clip}",
"type": "flux2"
}
},
"12": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "${model}",
"weight_dtype": "${dtype}"
}
},
"14": {
"class_type": "FluxGuidance",
"inputs": {
"conditioning": ["6", 0],
"guidance": "${guidance}"
}
},
"15": {
"class_type": "ConditioningZeroOut",
"inputs": {
"conditioning": ["6", 0]
}
},
"27": {
"class_type": "EmptyFlux2LatentImage",
"inputs": {
"width": "${width}",
"height": "${height}",
"batch_size": 1
}
},
"31": {
"class_type": "KSampler",
"inputs": {
"model": ["12", 0],
"seed": "${seed}",
"steps": "${steps}",
"cfg": "${cfg}",
"sampler_name": "${sampler}",
"scheduler": "${scheduler}",
"denoise": 1.0,
"positive": ["14", 0],
"negative": ["15", 0],
"latent_image": ["27", 0]
}
}
}

View File

@@ -0,0 +1,66 @@
{
"4": {
"class_type": "CheckpointLoaderSimple",
"inputs": {
"ckpt_name": "${model}"
}
},
"6": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "${prompt}",
"clip": ["4", 1]
}
},
"7": {
"class_type": "CLIPTextEncode",
"inputs": {
"text": "${negative}",
"clip": ["4", 1]
}
},
"8": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["31", 0],
"vae": ["4", 2]
}
},
"9": {
"class_type": "SaveImage",
"inputs": {
"filename_prefix": "imagen",
"images": ["8", 0]
}
},
"13": {
"class_type": "ModelSamplingSD3",
"inputs": {
"model": ["4", 0],
"shift": "${shift}"
}
},
"27": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": "${width}",
"height": "${height}",
"batch_size": 1
}
},
"31": {
"class_type": "KSampler",
"inputs": {
"model": ["13", 0],
"seed": "${seed}",
"steps": "${steps}",
"cfg": "${cfg}",
"sampler_name": "${sampler}",
"scheduler": "${scheduler}",
"denoise": 1.0,
"positive": ["6", 0],
"negative": ["7", 0],
"latent_image": ["27", 0]
}
}
}

View File

@@ -144,15 +144,54 @@ output:
cloud_sync: auto cloud_sync: auto
backends: 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: flux-schnell-local:
type: comfyui type: comfyui
base_url: http://mrock:8188 base_url: http://mrock:8188
workflow: flux1-schnell
# Filename of the unet checkpoint inside the ComfyUI server's # Filename of the unet checkpoint inside the ComfyUI server's
# models/unet/ directory. See docs/setup-comfyui-mrock.md. # models/unet/ directory.
model: flux1-schnell.safetensors 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_steps: 4
default_sampler: euler default_sampler: euler
default_scheduler: simple 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: mock:
type: mock type: mock