Files
LocalAI/pkg/grpc/interface.go
Pete 8a68f3571c feat(api): add POST /v1/images/upscale endpoint (#10227)
* feat(api): add POST /v1/images/upscale endpoint

Add a new image upscaling endpoint that accepts a source image and
returns an upscaled version. Supports selectable upscaler models
(e.g. realesrgan) and a configurable scale factor (2x or 4x).

- backend.proto: add UpscaleImage RPC and UpscaleImageRequest message
- pkg/grpc: implement UpscaleImage in Backend interface, client, server
  and embed shim
- core/backend/upscale.go: new backend helper (mirrors ImageGeneration)
- core/http/endpoints/openai/upscale.go: new multipart/form-data handler
- core/http/routes/openai.go: register POST /v1/images/upscale
- core/http/auth/features.go: gate upscale routes under FeatureImages
- backend/python/diffusers/backend.py: implement UpscaleImage — uses
  diffusers upscale pipeline when loaded, falls back to Lanczos resize

* fix(grpc): add UpscaleImage stub to Base backend

All Go backends embedding Base now satisfy the AIModel interface
without needing to implement UpscaleImage explicitly.

* fix(images): complete upscale endpoint integration

Store generated upscales under the served images directory, validate scale factors, document and advertise the endpoint, and add a functional Stable Diffusion x4 gallery model.

Assisted-by: Codex:gpt-5

---------

Co-authored-by: localai-org-maint-bot <306269227+localai-org-maint-bot@users.noreply.github.com>
2026-08-03 15:27:22 +02:00

99 lines
4.3 KiB
Go

package grpc
import (
"context"
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
)
type AIModel interface {
Busy() bool
Lock()
Unlock()
Locking() bool
Predict(*pb.PredictOptions) (string, error)
PredictStream(*pb.PredictOptions, chan string) error
Load(*pb.ModelOptions) error
Free() error
Embeddings(*pb.PredictOptions) ([]float32, error)
GenerateImage(*pb.GenerateImageRequest) error
UpscaleImage(*pb.UpscaleImageRequest) error
GenerateVideo(*pb.GenerateVideoRequest) error
Generate3D(*pb.Generate3DRequest) error
Detect(*pb.DetectOptions) (pb.DetectResponse, error)
Depth(*pb.DepthRequest) (pb.DepthResponse, error)
FaceVerify(*pb.FaceVerifyRequest) (pb.FaceVerifyResponse, error)
FaceAnalyze(*pb.FaceAnalyzeRequest) (pb.FaceAnalyzeResponse, error)
VoiceVerify(*pb.VoiceVerifyRequest) (pb.VoiceVerifyResponse, error)
VoiceAnalyze(*pb.VoiceAnalyzeRequest) (pb.VoiceAnalyzeResponse, error)
VoiceEmbed(*pb.VoiceEmbedRequest) (pb.VoiceEmbedResponse, error)
AudioTranscription(context.Context, *pb.TranscriptRequest) (pb.TranscriptResult, error)
AudioTranscriptionStream(context.Context, *pb.TranscriptRequest, chan *pb.TranscriptStreamResponse) error
AudioTranscriptionLive(in <-chan *pb.TranscriptLiveRequest, out chan<- *pb.TranscriptLiveResponse) error
TTS(*pb.TTSRequest) error
TTSStream(*pb.TTSRequest, chan []byte) error
SoundGeneration(*pb.SoundGenerationRequest) error
TokenizeString(*pb.PredictOptions) (pb.TokenizationResponse, error)
Detokenize(*pb.DetokenizeRequest) (pb.DetokenizeResponse, error)
Status() (pb.StatusResponse, error)
StoresSet(*pb.StoresSetOptions) error
StoresDelete(*pb.StoresDeleteOptions) error
StoresGet(*pb.StoresGetOptions) (pb.StoresGetResult, error)
StoresFind(*pb.StoresFindOptions) (pb.StoresFindResult, error)
VAD(*pb.VADRequest) (pb.VADResponse, error)
Diarize(*pb.DiarizeRequest) (pb.DiarizeResponse, error)
SoundDetection(context.Context, *pb.SoundDetectionRequest) (*pb.SoundDetectionResponse, error)
AudioEncode(*pb.AudioEncodeRequest) (*pb.AudioEncodeResult, error)
AudioDecode(*pb.AudioDecodeRequest) (*pb.AudioDecodeResult, error)
AudioTransform(*pb.AudioTransformRequest) (*pb.AudioTransformResult, error)
AudioTransformStream(in <-chan *pb.AudioTransformFrameRequest, out chan<- *pb.AudioTransformFrameResponse) error
AudioToAudioStream(in <-chan *pb.AudioToAudioRequest, out chan<- *pb.AudioToAudioResponse) error
// Forward proxies a raw HTTP request to an upstream provider for
// passthrough-mode cloud-proxy backends. ctx is the gRPC stream
// context — cancellation propagates to the upstream HTTP request
// so client disconnect closes the upstream connection.
Forward(ctx context.Context, in <-chan *pb.ForwardRequest, out chan<- *pb.ForwardReply) error
ModelMetadata(*pb.ModelOptions) (*pb.ModelMetadataResponse, error)
// Fine-tuning
StartFineTune(*pb.FineTuneRequest) (*pb.FineTuneJobResult, error)
FineTuneProgress(*pb.FineTuneProgressRequest, chan *pb.FineTuneProgressUpdate) error
StopFineTune(*pb.FineTuneStopRequest) error
ListCheckpoints(*pb.ListCheckpointsRequest) (*pb.ListCheckpointsResponse, error)
ExportModel(*pb.ExportModelRequest) error
// Quantization
StartQuantization(*pb.QuantizationRequest) (*pb.QuantizationJobResult, error)
QuantizationProgress(*pb.QuantizationProgressRequest, chan *pb.QuantizationProgressUpdate) error
StopQuantization(*pb.QuantizationStopRequest) error
}
func newReply(s string) *pb.Reply {
return &pb.Reply{Message: []byte(s)}
}
// AIModelRich is an optional extension to AIModel for backends that
// can produce a full *pb.Reply — including tool-call deltas and
// usage tokens — rather than just a content string. The gRPC server
// type-asserts and prefers the rich path when implemented; otherwise
// it wraps Predict's string return in a Reply.
//
// Cloud-proxy translate mode is the motivating use case: the upstream
// emits structured tool_calls that would be lost through the legacy
// (string, error) signature.
//
// PredictStreamRich contract: send replies into the channel and
// return when finished. Do NOT close the channel — the server closes
// it after the call returns. This is opposite to legacy PredictStream
// which expects the impl to defer close().
type AIModelRich interface {
PredictRich(*pb.PredictOptions) (*pb.Reply, error)
PredictStreamRich(*pb.PredictOptions, chan<- *pb.Reply) error
}