DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 11:26:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(server): add ADetailer support to image generation (#2164)

Browse Source
This commit is contained in:
losewayy authored and GitHub committed 2026-10-21 23:11:36 +08:00
1 parent 0518b34374
commit 845646b034
10 files changed
+515 -61
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/detailer.cpp
+28 -10
View File
@@ -291,7 +291,9 @@ static void filter_and_sort_detections(std::vector<ADetailerDetection>* detectio
std::partial_sort(detections->begin(),
detections->begin() + params.mask_k_largest,
detections->end(),
[](const auto& a, const auto& b) { return detection_area(a) > detection_area(b); });
[&](const auto& a, const auto& b) {
return params.mask_filter_by_confidence ? a.confidence > b.confidence : detection_area(a) > detection_area(b);
});
detections->resize(params.mask_k_largest);
}
@@ -545,7 +547,16 @@ static sd_image_t resize_crop_mask(const Mask& source, const CropRegion& crop, i
return output;
}
static sd_image_t copy_as_rgb(const sd_image_t& source) {
static sd_image_t copy_for_detailing(const sd_image_t& source) {
if (source.channel == 4) {
sd_image_t output = source;
size_t bytes = static_cast<size_t>(source.width) * source.height * source.channel;
output.data = static_cast<uint8_t*>(malloc(bytes));
if (output.data != nullptr) {
memcpy(output.data, source.data, bytes);
}
return output;
}
CropRegion full{0, 0, static_cast<int>(source.width), static_cast<int>(source.height)};
return resize_crop_image(source, full, source.width, source.height);
}
@@ -566,7 +577,7 @@ static void composite_crop(sd_image_t* destination,
continue;
}
float source_x = (x - crop.x1 + 0.5f) * scale_x - 0.5f;
size_t destination_index = (static_cast<size_t>(y) * destination->width + x) * 3;
size_t destination_index = (static_cast<size_t>(y) * destination->width + x) * destination->channel;
for (int c = 0; c < 3; ++c) {
float generated_value = bilinear_channel(generated, source_x, source_y, c) * 255.f;
float original_value = destination->data[destination_index + c];
@@ -787,6 +798,10 @@ static bool parse_adetailer_params(const sd_adetailer_params_t& public_params,
ok = parse_int(value, &params->max_detections);
} else if (key == "mask_k_largest") {
ok = parse_int(value, &params->mask_k_largest);
} else if (key == "mask_filter_method") {
const std::string method = lower_copy(value);
ok = method == "area" || method == "confidence";
params->mask_filter_by_confidence = method == "confidence";
} else if (key == "mask_min_ratio") {
ok = parse_float(value, &params->mask_min_ratio);
} else if (key == "mask_max_ratio") {
@@ -805,6 +820,8 @@ static bool parse_adetailer_params(const sd_adetailer_params_t& public_params,
ok = parse_int(value, &params->mask_blur);
} else if (key == "inpaint_padding") {
ok = parse_int(value, &params->inpaint_padding);
} else if (key == "inpaint_only_masked") {
ok = parse_bool(value, &params->inpaint_only_masked);
} else if (key == "inpaint_width") {
ok = parse_int(value, &params->inpaint_width);
} else if (key == "inpaint_height") {
@@ -920,7 +937,7 @@ bool adetail_image(adetailer_ctx_t* context,
filter_and_sort_detections(&detections, input_image.width, input_image.height, params);
auto masks = make_masks(detections, input_image.width, input_image.height, params);
sd_image_t current = copy_as_rgb(input_image);
sd_image_t current = copy_for_detailing(input_image);
if (current.data == nullptr) {
return false;
}
@@ -939,12 +956,13 @@ bool adetail_image(adetailer_ctx_t* context,
if (!mask_bbox(masks[i], &crop)) {
continue;
}
crop = expand_crop(crop,
current.width,
current.height,
params.inpaint_padding,
params.inpaint_width,
params.inpaint_height);
crop = params.inpaint_only_masked ? expand_crop(crop,
current.width,
current.height,
params.inpaint_padding,
params.inpaint_width,
params.inpaint_height)
: CropRegion{0, 0, static_cast<int>(current.width), static_cast<int>(current.height)};
sd_image_t local_image = resize_crop_image(current, crop, params.inpaint_width, params.inpaint_height);
sd_image_t local_mask = resize_crop_mask(masks[i], crop, params.inpaint_width, params.inpaint_height);
if (local_image.data == nullptr || local_mask.data == nullptr) {
src/detailer.h
+26 -24
View File
@@ -27,30 +27,32 @@ enum ADetailerSort {
};
struct ADetailerParams {
const char* prompt = nullptr;
const char* negative_prompt = nullptr;
int input_size = 640;
float confidence = 0.3f;
float nms_threshold = 0.45f;
int max_detections = 100;
int mask_k_largest = 0;
float mask_min_ratio = 0.f;
float mask_max_ratio = 1.f;
int dilate_erode = 4;
int x_offset = 0;
int y_offset = 0;
bool merge_masks = false;
bool invert_mask = false;
int mask_blur = 4;
int inpaint_padding = 32;
int inpaint_width = 512;
int inpaint_height = 512;
float denoising_strength = 0.4f;
int steps = 0;
float cfg_scale = -1.f;
sample_method_t sample_method = SAMPLE_METHOD_COUNT;
scheduler_t scheduler = SCHEDULER_COUNT;
ADetailerSort sort_by = ADETAILER_SORT_NONE;
const char* prompt = nullptr;
const char* negative_prompt = nullptr;
int input_size = 640;
float confidence = 0.3f;
float nms_threshold = 0.45f;
int max_detections = 100;
int mask_k_largest = 0;
bool mask_filter_by_confidence = false;
float mask_min_ratio = 0.f;
float mask_max_ratio = 1.f;
int dilate_erode = 4;
int x_offset = 0;
int y_offset = 0;
bool merge_masks = false;
bool invert_mask = false;
int mask_blur = 4;
int inpaint_padding = 32;
bool inpaint_only_masked = true;
int inpaint_width = 512;
int inpaint_height = 512;
float denoising_strength = 0.4f;
int steps = 0;
float cfg_scale = -1.f;
sample_method_t sample_method = SAMPLE_METHOD_COUNT;
scheduler_t scheduler = SCHEDULER_COUNT;
ADetailerSort sort_by = ADETAILER_SORT_NONE;
};
struct ADetailerGGML {