steveandClaude Fable 5
5f175ecf82
- videogen.LipSyncer/LipsyncProvider: SadTalker talking heads via
POST /upstream/<id>/v1/talking_head (multipart image+audio parts,
still/enhance/preprocess flags) -> mp4.
- videogen.VideoBackgroundRemover/VideoBackgroundRemovalProvider:
POST /upstream/<id>/v1/video/matte (output greenscreen_mp4|alpha_webm).
- videogen.VideoUpscaler/VideoUpscaleProvider:
POST /upstream/<id>/v1/video/upscale (scale 2|4).
- videogen.Chainer/ChainerProvider: async long-video chain-job client —
SubmitChain (JSON POST /v1/video/chain, init_image_b64), ChainStatus
(GET /v1/jobs/{id}, tolerant segment-id decode), ChainResult,
ChainSegmentResult (partial delivery after mid-chain failure); hostile
job-id path rejection.
- Shared singleVideoResult validation (positive video evidence) + a
videoInputFilename hint helper; httptest contract tests per surface;
ADR-0025 (index row deferred — MJ-A backfills the ADR index table and
parallel edits would conflict).
Co-Authored-By: Claude Fable 5 <[email protected]>
94 lines
3.2 KiB
Go
94 lines
3.2 KiB
Go
package videogen
|
|
|
|
import "context"
|
|
|
|
// LipsyncRequest asks a talking-head backend (SadTalker style) to animate a
|
|
// still portrait so it speaks the given audio. Zero values mean "backend
|
|
// default" (ADR-0025).
|
|
type LipsyncRequest struct {
|
|
// Image is the portrait to animate. Required.
|
|
Image Image
|
|
|
|
// Audio is the encoded speech the head lip-syncs to. Required. Carried
|
|
// as bytes (never a URL), mirroring audio.TranscriptionRequest.
|
|
Audio []byte
|
|
|
|
// AudioMIME is the audio MIME type (e.g. "audio/wav"); "" = let the
|
|
// backend sniff it.
|
|
AudioMIME string
|
|
|
|
// AudioFilename is the multipart filename hint some backends key their
|
|
// format detection on; "" derives one from AudioMIME or falls back to
|
|
// "audio".
|
|
AudioFilename string
|
|
|
|
// Still reduces head motion to blinks and lip movement (less uncanny on
|
|
// formal portraits); false = backend default motion.
|
|
Still bool
|
|
|
|
// Enhance runs the backend's face enhancer over the output frames.
|
|
Enhance bool
|
|
|
|
// Preprocess selects how the backend frames the face: "crop" (animate
|
|
// the face crop) or "full" (paste the animated face back into the whole
|
|
// image); "" = backend default.
|
|
Preprocess string
|
|
}
|
|
|
|
// LipsyncOption mutates a LipsyncRequest before it is sent.
|
|
type LipsyncOption func(*LipsyncRequest)
|
|
|
|
// WithLipsyncStill reduces head motion to blinks and lip movement.
|
|
func WithLipsyncStill() LipsyncOption { return func(r *LipsyncRequest) { r.Still = true } }
|
|
|
|
// WithLipsyncEnhance runs the backend's face enhancer over the output.
|
|
func WithLipsyncEnhance() LipsyncOption { return func(r *LipsyncRequest) { r.Enhance = true } }
|
|
|
|
// WithLipsyncPreprocess selects the face framing ("crop" or "full").
|
|
func WithLipsyncPreprocess(p string) LipsyncOption {
|
|
return func(r *LipsyncRequest) { r.Preprocess = p }
|
|
}
|
|
|
|
// Apply returns a copy of the request with all options applied.
|
|
func (r LipsyncRequest) Apply(opts ...LipsyncOption) LipsyncRequest {
|
|
for _, opt := range opts {
|
|
opt(&r)
|
|
}
|
|
return r
|
|
}
|
|
|
|
// LipSyncer animates still portraits into talking-head clips. Its own small
|
|
// interface rather than a method on Model: lip-syncers are not text-to-video
|
|
// generators — they bind to a different backend id entirely.
|
|
type LipSyncer interface {
|
|
// Lipsync returns the talking-head clip. Generation is slow (minutes);
|
|
// bound the call with a context deadline.
|
|
Lipsync(ctx context.Context, req LipsyncRequest, opts ...LipsyncOption) (*Result, error)
|
|
}
|
|
|
|
// LipsyncModelOption configures a LipSyncer at construction time. Reserved
|
|
// for future per-model settings.
|
|
type LipsyncModelOption func(*LipsyncModelConfig)
|
|
|
|
// LipsyncModelConfig carries per-model construction settings.
|
|
type LipsyncModelConfig struct{}
|
|
|
|
// ApplyLipsyncModelOptions folds options into a config.
|
|
func ApplyLipsyncModelOptions(opts []LipsyncModelOption) LipsyncModelConfig {
|
|
var cfg LipsyncModelConfig
|
|
for _, opt := range opts {
|
|
opt(&cfg)
|
|
}
|
|
return cfg
|
|
}
|
|
|
|
// LipsyncProvider mints LipSyncers bound to one backend.
|
|
type LipsyncProvider interface {
|
|
// Name is the registry identifier for the provider.
|
|
Name() string
|
|
|
|
// LipsyncModel returns a LipSyncer bound to the given id (passed through
|
|
// to the backend verbatim; no catalog validation).
|
|
LipsyncModel(id string, opts ...LipsyncModelOption) (LipSyncer, error)
|
|
}
|