Files
majordomo/provider/llamaswap/image.go
T
steve a213c18263
CI / Tidy (pull_request) Successful in 9m24s
CI / Build & Test (pull_request) Successful in 9m45s
Adversarial Review (Gadfly) / review (pull_request) Successful in 11m30s
fix(llamaswap): use A1111 /sdapi/v1/txt2img so seed is honored
The OpenAI /v1/images/generations endpoint ignores `seed` on our
stable-diffusion.cpp build — every render of a given prompt comes back
byte-identical, so a drawbot batch of N collapsed to one image. Switch the
image provider to sd-server's A1111 /sdapi/v1/txt2img endpoint, which honors
`seed` (verified live: distinct seeds -> distinct images on SDXL and
Qwen-Image). Size is split into width/height; llama-swap still routes by the
`model` field. Tests + ADR-0016 updated.
2026-06-28 22:56:25 -04:00

138 lines
4.5 KiB
Go

package llamaswap
import (
"context"
"encoding/base64"
"fmt"
"net/http"
"strconv"
"strings"
"gitea.stevedudenhoeffer.com/steve/majordomo/imagegen"
"gitea.stevedudenhoeffer.com/steve/majordomo/llm"
)
// ImageModel implements imagegen.Provider, binding an image-generation model
// served by llama-swap (routed to a stable-diffusion.cpp upstream). The id is
// passed through verbatim and selects which upstream llama-swap loads.
func (p *Provider) ImageModel(id string, opts ...imagegen.ModelOption) (imagegen.Model, error) {
if p.baseURL == "" {
return nil, fmt.Errorf("llama-swap provider %q: no base URL configured (set one via WithBaseURL or an LLM_* env DSN)", p.name)
}
_ = imagegen.ApplyModelOptions(opts)
return &imageModel{p: p, id: id}, nil
}
type imageModel struct {
p *Provider
id string
}
// txt2imgRequest is the stable-diffusion.cpp sd-server A1111 request shape
// (POST /sdapi/v1/txt2img). We use this endpoint rather than the OpenAI
// /v1/images/generations one because that endpoint IGNORES `seed` on this
// sd-server build — every render of a given prompt comes back byte-identical,
// so a batch of N collapses to one image. /sdapi/v1/txt2img honours `seed`,
// giving real variety. llama-swap still routes by the `model` field in the
// body. Optional fields are pointers/omitempty so an unset value falls back to
// the model's baked default (the per-model --steps/--cfg-scale/etc. flags).
type txt2imgRequest struct {
Model string `json:"model"`
Prompt string `json:"prompt"`
NegativePrompt string `json:"negative_prompt,omitempty"`
Seed *int64 `json:"seed,omitempty"`
Steps *int `json:"steps,omitempty"`
CFGScale *float64 `json:"cfg_scale,omitempty"`
Width *int `json:"width,omitempty"`
Height *int `json:"height,omitempty"`
SampleMethod string `json:"sample_method,omitempty"`
BatchCount int `json:"batch_count,omitempty"`
}
type txt2imgResponse struct {
Images []string `json:"images"`
}
// Generate implements imagegen.Model via POST {base}/sdapi/v1/txt2img.
func (m *imageModel) Generate(ctx context.Context, req imagegen.Request, opts ...imagegen.Option) (*imagegen.Result, error) {
req = req.Apply(opts...)
if strings.TrimSpace(req.Prompt) == "" {
return nil, fmt.Errorf("%w: image generation requires a prompt", llm.ErrUnsupported)
}
if req.N < 0 {
return nil, fmt.Errorf("%w: image count N must be >= 0, got %d", llm.ErrUnsupported, req.N)
}
width, height, err := parseSize(req.Size)
if err != nil {
return nil, fmt.Errorf("%w: %v", llm.ErrUnsupported, err)
}
wire := txt2imgRequest{
Model: m.id,
Prompt: req.Prompt,
NegativePrompt: req.NegativePrompt,
Seed: req.Seed,
Steps: req.Steps,
CFGScale: req.CFGScale,
Width: width,
Height: height,
SampleMethod: req.Sampler,
BatchCount: req.N,
}
var resp txt2imgResponse
if err := m.p.doJSON(ctx, http.MethodPost, "/sdapi/v1/txt2img", m.id, &wire, &resp); err != nil {
return nil, err
}
out := &imagegen.Result{Raw: &resp}
for i, b64 := range resp.Images {
if b64 == "" {
continue
}
raw, err := base64.StdEncoding.DecodeString(b64)
if err != nil {
return nil, fmt.Errorf("llama-swap: decode image %d: %w", i, err)
}
out.Images = append(out.Images, llm.ImagePart{MIME: sniffImageMIME(raw), Data: raw})
}
if len(out.Images) == 0 {
return nil, &llm.APIError{
Provider: m.p.name,
Model: m.id,
Message: "image response contained no images",
}
}
return out, nil
}
// parseSize splits a "WxH" string into width/height pointers. "" yields
// (nil, nil) so the model's own default resolution applies.
func parseSize(size string) (*int, *int, error) {
size = strings.TrimSpace(size)
if size == "" {
return nil, nil, nil
}
parts := strings.SplitN(strings.ToLower(size), "x", 2)
if len(parts) != 2 {
return nil, nil, fmt.Errorf("invalid size %q (want WxH)", size)
}
w, err1 := strconv.Atoi(strings.TrimSpace(parts[0]))
h, err2 := strconv.Atoi(strings.TrimSpace(parts[1]))
if err1 != nil || err2 != nil || w <= 0 || h <= 0 {
return nil, nil, fmt.Errorf("invalid size %q (want WxH)", size)
}
return &w, &h, nil
}
// sniffImageMIME identifies the image format from its leading bytes, defaulting
// to image/png (stable-diffusion.cpp emits PNG) when detection is inconclusive.
func sniffImageMIME(data []byte) string {
mime := http.DetectContentType(data)
if !strings.HasPrefix(mime, "image/") {
return "image/png"
}
return mime
}