feat: wave-3 image + document surfaces — segmentation, colorize, face restore, ocr (ADR-0023)
- imagegen.Segmenter/SegmentationProvider: prompted mask via POST /upstream/<id>/v1/segment (file, prompt[, threshold], output=mask); white = prompted region, EditRequest.Mask polarity. - imagegen.Colorizer/ColorizeProvider: POST /upstream/<id>/v1/colorize. - imagegen.FaceRestorer/FaceRestoreProvider: POST /upstream/<id>/v1/restore_faces (upscale 1|2). - New ocr leaf package (Request/Page/Result, Recognize) + llamaswap OCRModel: POST /upstream/<id>/v1/ocr (file[, langs, max_pages]), tolerant per-page decode (join lines when page text absent), Raw escape hatch. - httptest contract tests per surface; ADR-0023; ADR index backfilled (0020-0022 rows were missing). Co-Authored-By: Claude Fable 5 <[email protected]>
This commit is contained in:
@@ -0,0 +1,106 @@
|
||||
// restore.go implements the imagegen.ColorizeProvider and
|
||||
// imagegen.FaceRestoreProvider surfaces against the mediautils shim reached
|
||||
// through llama-swap's /upstream passthrough (ADR-0023):
|
||||
//
|
||||
// colorize POST /upstream/<id>/v1/colorize (DDColor)
|
||||
// restore_faces POST /upstream/<id>/v1/restore_faces (GFPGAN)
|
||||
//
|
||||
// Both are one-file multipart in, one PNG out, mirroring mediautil.go.
|
||||
package llamaswap
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"strconv"
|
||||
|
||||
"gitea.stevedudenhoeffer.com/steve/majordomo/imagegen"
|
||||
"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
|
||||
)
|
||||
|
||||
// --- colorize ---
|
||||
|
||||
// ColorizeModel implements imagegen.ColorizeProvider against the mediautils
|
||||
// shim's POST /v1/colorize. The id selects which upstream llama-swap loads.
|
||||
func (p *Provider) ColorizeModel(id string, opts ...imagegen.ColorizeModelOption) (imagegen.Colorizer, error) {
|
||||
if err := p.requireBaseURL(); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
_ = imagegen.ApplyColorizeModelOptions(opts)
|
||||
return &colorizeModel{p: p, id: id}, nil
|
||||
}
|
||||
|
||||
type colorizeModel struct {
|
||||
p *Provider
|
||||
id string
|
||||
}
|
||||
|
||||
// Colorize implements imagegen.Colorizer.
|
||||
func (m *colorizeModel) Colorize(ctx context.Context, req imagegen.ColorizeRequest, opts ...imagegen.ColorizeOption) (*imagegen.Result, error) {
|
||||
req = req.Apply(opts...)
|
||||
if len(req.Image.Data) == 0 {
|
||||
return nil, fmt.Errorf("%w: colorization requires an image", llm.ErrUnsupported)
|
||||
}
|
||||
path, err := upstreamPath(m.id, "/v1/colorize")
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
body, contentType, err := buildMultipart("build colorize form",
|
||||
filePart{field: "file", filename: "image.png", data: req.Image.Data},
|
||||
nil)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, contentType, body, maxImageResponseBytes)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return singleImageResult(m.p.name, m.id, "colorize", raw, respType)
|
||||
}
|
||||
|
||||
// --- face restoration ---
|
||||
|
||||
// FaceRestoreModel implements imagegen.FaceRestoreProvider against the
|
||||
// mediautils shim's POST /v1/restore_faces.
|
||||
func (p *Provider) FaceRestoreModel(id string, opts ...imagegen.FaceRestoreModelOption) (imagegen.FaceRestorer, error) {
|
||||
if err := p.requireBaseURL(); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
_ = imagegen.ApplyFaceRestoreModelOptions(opts)
|
||||
return &faceRestoreModel{p: p, id: id}, nil
|
||||
}
|
||||
|
||||
type faceRestoreModel struct {
|
||||
p *Provider
|
||||
id string
|
||||
}
|
||||
|
||||
// RestoreFaces implements imagegen.FaceRestorer.
|
||||
func (m *faceRestoreModel) RestoreFaces(ctx context.Context, req imagegen.FaceRestoreRequest, opts ...imagegen.FaceRestoreOption) (*imagegen.Result, error) {
|
||||
req = req.Apply(opts...)
|
||||
if len(req.Image.Data) == 0 {
|
||||
return nil, fmt.Errorf("%w: face restoration requires an image", llm.ErrUnsupported)
|
||||
}
|
||||
if req.Upscale != 0 && req.Upscale != 1 && req.Upscale != 2 {
|
||||
return nil, fmt.Errorf("%w: face-restore upscale must be 1 or 2, got %d", llm.ErrUnsupported, req.Upscale)
|
||||
}
|
||||
path, err := upstreamPath(m.id, "/v1/restore_faces")
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
upscale := ""
|
||||
if req.Upscale != 0 {
|
||||
upscale = strconv.Itoa(req.Upscale)
|
||||
}
|
||||
body, contentType, err := buildMultipart("build restore-faces form",
|
||||
filePart{field: "file", filename: "image.png", data: req.Image.Data},
|
||||
[]formField{{"upscale", upscale, false}})
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
raw, respType, err := m.p.doRaw(ctx, http.MethodPost, path, m.id, contentType, body, maxImageResponseBytes)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return singleImageResult(m.p.name, m.id, "face restoration", raw, respType)
|
||||
}
|
||||
Reference in New Issue
Block a user