feat: add configurable reference image processing for edit models (#1780)

This commit is contained in:
stduhpf
2026-07-14 16:58:22 +02:00
committed by GitHub
parent b5d812008e
commit 74bce049d0
15 changed files with 551 additions and 159 deletions

View File

@@ -7,6 +7,7 @@
#include "core/tensor_ggml.hpp"
#include "core/util.h"
#include "model/diffusion/model.hpp"
#include "model/te/clip.hpp"
#include "model/te/llm.hpp"
#include "model/te/t5.hpp"
@@ -106,6 +107,7 @@ struct ConditionerParams {
int height = -1;
bool zero_out_masked = false;
const std::vector<sd::Tensor<float>>* ref_images = nullptr; // for qwen image edit
RefImageParams ref_image_params;
};
struct Conditioner {
@@ -1993,6 +1995,54 @@ struct LLMEmbedder : public Conditioner {
return new_hidden_states;
}
void resize_image_dims(int height, int width, int& h_bar, int& w_bar, int factor, int min_size, int max_size, RefImageResizeMode mode) {
if (min_size > 0 && min_size == max_size) {
if (mode == RefImageResizeMode::AREA) {
double beta = std::sqrt(static_cast<double>(min_size) / (static_cast<double>(height) * width));
h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(height * beta / factor)) * static_cast<int>(factor));
w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(width * beta / factor)) * static_cast<int>(factor));
} else if (mode == RefImageResizeMode::LONGEST_SIDE) {
int current_max_side = std::max(height, width);
double beta = static_cast<double>(min_size) / current_max_side;
h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(height * beta / factor)) * static_cast<int>(factor));
w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(width * beta / factor)) * static_cast<int>(factor));
}
return;
}
if (mode == RefImageResizeMode::AREA) {
double current_area = static_cast<double>(h_bar) * w_bar;
if (max_size > 0 && current_area > max_size) {
double beta = std::sqrt((static_cast<double>(height) * width) / static_cast<double>(max_size));
h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(height / beta / factor)) * static_cast<int>(factor));
w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(width / beta / factor)) * static_cast<int>(factor));
} else if (min_size > 0 && current_area < min_size) {
double beta = std::sqrt(static_cast<double>(min_size) / (static_cast<double>(height) * width));
h_bar = static_cast<int>(std::ceil(height * beta / factor)) * static_cast<int>(factor);
w_bar = static_cast<int>(std::ceil(width * beta / factor)) * static_cast<int>(factor);
}
} else if (mode == RefImageResizeMode::LONGEST_SIDE) {
int current_max_side = std::max(height, width);
if (max_size > 0 && current_max_side > max_size) {
double beta = static_cast<double>(max_size) / current_max_side;
h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(height * beta / factor)) * static_cast<int>(factor));
w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(width * beta / factor)) * static_cast<int>(factor));
} else if (min_size > 0 && current_max_side < min_size) {
double beta = static_cast<double>(min_size) / current_max_side;
h_bar = static_cast<int>(std::ceil(height * beta / factor)) * static_cast<int>(factor);
w_bar = static_cast<int>(std::ceil(width * beta / factor)) * static_cast<int>(factor);
}
}
}
SDCondition get_learned_condition(int n_threads,
const ConditionerParams& conditioner_params) override {
std::string prompt;
@@ -2007,7 +2057,8 @@ struct LLMEmbedder : public Conditioner {
bool spell_quotes = false;
std::set<int> out_layers;
int64_t t0 = ggml_time_ms();
int64_t t0 = ggml_time_ms();
RefImageResizeMode resize_mode = conditioner_params.ref_image_params.vlm_resize_mode;
if (sd_version_is_lingbot_video(version)) {
const int pad_token = 151643;
@@ -2040,28 +2091,35 @@ struct LLMEmbedder : public Conditioner {
for (int i = 0; i < conditioner_params.ref_images->size(); i++) {
const auto& image = (*conditioner_params.ref_images)[i];
double factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
const int factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
int height = static_cast<int>(image.shape()[1]);
int width = static_cast<int>(image.shape()[0]);
int min_pixels = static_cast<int>(4 * factor * factor);
int max_pixels = static_cast<int>(16384 * factor * factor);
int h_bar = std::max(static_cast<int>(factor), static_cast<int>(std::round(height / factor) * factor));
int w_bar = std::max(static_cast<int>(factor), static_cast<int>(std::round(width / factor) * factor));
int min_pixels = conditioner_params.ref_image_params.vlm_min_size;
if (min_pixels <= 0) {
if (resize_mode == RefImageResizeMode::AREA) {
min_pixels = static_cast<int>(4 * factor * factor);
} else {
min_pixels = static_cast<int>(2 * factor);
}
}
int max_pixels = conditioner_params.ref_image_params.vlm_max_size;
if (max_pixels <= 0) {
if (resize_mode == RefImageResizeMode::AREA) {
max_pixels = static_cast<int>(16384 * factor * factor);
} else {
max_pixels = static_cast<int>(128 * factor);
}
}
int h_bar = std::max(factor, static_cast<int>(std::round(static_cast<double>(height) / factor) * factor));
int w_bar = std::max(factor, static_cast<int>(std::round(static_cast<double>(width) / factor) * factor));
if (std::max(height, width) > 200 * std::min(height, width)) {
LOG_WARN("LingBotVideo image aspect ratio is very large: %dx%d", width, height);
}
if (h_bar * w_bar > max_pixels) {
double beta = std::sqrt((height * width) / static_cast<double>(max_pixels));
h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(height / beta / factor)) * static_cast<int>(factor));
w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(width / beta / factor)) * static_cast<int>(factor));
} else if (h_bar * w_bar < min_pixels) {
double beta = std::sqrt(static_cast<double>(min_pixels) / (height * width));
h_bar = static_cast<int>(std::ceil(height * beta / factor)) * static_cast<int>(factor);
w_bar = static_cast<int>(std::ceil(width * beta / factor)) * static_cast<int>(factor);
}
resize_image_dims(height, width, h_bar, w_bar, factor, min_pixels, max_pixels, resize_mode);
LOG_DEBUG("resize LingBotVideo ref image %d from %dx%d to %dx%d", i, height, width, h_bar, w_bar);
auto resized_image = clip_preprocess(image, w_bar, h_bar);
@@ -2092,30 +2150,33 @@ struct LLMEmbedder : public Conditioner {
prompt_template_encode_start_idx = 64;
int image_embed_idx = 64 + 6;
int min_pixels = 384 * 384;
int max_pixels = 560 * 560;
int min_pixels = conditioner_params.ref_image_params.vlm_min_size;
if (min_pixels <= 0) {
min_pixels = 384;
if (resize_mode == RefImageResizeMode::AREA) {
min_pixels *= min_pixels;
}
}
int max_pixels = conditioner_params.ref_image_params.vlm_max_size;
if (max_pixels <= 0) {
max_pixels = 560;
if (resize_mode == RefImageResizeMode::AREA) {
max_pixels *= max_pixels;
}
}
std::string placeholder = "<|image_pad|>";
std::string img_prompt;
for (int i = 0; i < conditioner_params.ref_images->size(); i++) {
const auto& image = (*conditioner_params.ref_images)[i];
double factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
const int factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
int height = static_cast<int>(image.shape()[1]);
int width = static_cast<int>(image.shape()[0]);
int h_bar = static_cast<int>(std::round(height / factor) * factor);
int w_bar = static_cast<int>(std::round(width / factor) * factor);
int h_bar = static_cast<int>(std::round(static_cast<double>(height) / factor) * factor);
int w_bar = static_cast<int>(std::round(static_cast<double>(width) / factor) * factor);
if (static_cast<double>(h_bar) * w_bar > max_pixels) {
double beta = std::sqrt((height * width) / static_cast<double>(max_pixels));
h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(height / beta / factor)) * static_cast<int>(factor));
w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(width / beta / factor)) * static_cast<int>(factor));
} else if (static_cast<double>(h_bar) * w_bar < min_pixels) {
double beta = std::sqrt(static_cast<double>(min_pixels) / (height * width));
h_bar = static_cast<int>(std::ceil(height * beta / factor)) * static_cast<int>(factor);
w_bar = static_cast<int>(std::ceil(width * beta / factor)) * static_cast<int>(factor);
}
resize_image_dims(height, width, h_bar, w_bar, factor, min_pixels, max_pixels, resize_mode);
LOG_DEBUG("resize conditioner ref image %d from %dx%d to %dx%d", i, height, width, h_bar, w_bar);
@@ -2170,16 +2231,33 @@ struct LLMEmbedder : public Conditioner {
std::string img_prompt;
const std::string placeholder = "<|image_pad|>";
int min_pixels = conditioner_params.ref_image_params.vlm_min_size;
if (min_pixels <= 0) {
min_pixels = 384;
if (resize_mode == RefImageResizeMode::AREA) {
min_pixels *= min_pixels;
}
}
int max_pixels = conditioner_params.ref_image_params.vlm_max_size;
if (max_pixels <= 0) {
max_pixels = 384;
if (resize_mode == RefImageResizeMode::AREA) {
max_pixels *= max_pixels;
}
}
for (int i = 0; i < conditioner_params.ref_images->size(); i++) {
const auto& image = (*conditioner_params.ref_images)[i];
double factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
const int factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
int height = static_cast<int>(image.shape()[1]);
int width = static_cast<int>(image.shape()[0]);
double beta = std::sqrt((384.0 * 384.0) / (static_cast<double>(height) * static_cast<double>(width)));
int h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(height * beta / factor)) * static_cast<int>(factor));
int w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(width * beta / factor)) * static_cast<int>(factor));
int h_bar = std::max(factor,
static_cast<int>(std::round(static_cast<double>(height) / factor)) * factor);
int w_bar = std::max(factor,
static_cast<int>(std::round(static_cast<double>(width) / factor)) * factor);
resize_image_dims(height, width, h_bar, w_bar, factor, min_pixels, max_pixels, resize_mode);
LOG_DEBUG("resize conditioner ref image %d from %dx%d to %dx%d", i, height, width, h_bar, w_bar);
@@ -2221,17 +2299,33 @@ struct LLMEmbedder : public Conditioner {
if (llm->enable_vision && conditioner_params.ref_images != nullptr && !conditioner_params.ref_images->empty()) {
std::string img_prompt = "";
const std::string placeholder = "<|image_pad|>";
int min_pixels = conditioner_params.ref_image_params.vlm_min_size;
if (min_pixels <= 0) {
min_pixels = 384;
if (resize_mode == RefImageResizeMode::AREA) {
min_pixels *= min_pixels;
}
}
int max_pixels = conditioner_params.ref_image_params.vlm_max_size;
if (max_pixels <= 0) {
max_pixels = 1024;
if (resize_mode == RefImageResizeMode::AREA) {
max_pixels *= max_pixels;
}
}
for (int i = 0; i < conditioner_params.ref_images->size(); i++) {
const auto& image = (*conditioner_params.ref_images)[i];
double factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
const int factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
int height = static_cast<int>(image.shape()[1]);
int width = static_cast<int>(image.shape()[0]);
double beta = std::sqrt((384.0 * 384.0) / (static_cast<double>(height) * static_cast<double>(width)));
int h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(height * beta / factor)) * static_cast<int>(factor));
int w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::round(width * beta / factor)) * static_cast<int>(factor));
int h_bar = std::max(factor,
static_cast<int>(std::round(static_cast<double>(height) / factor)) * factor);
int w_bar = std::max(factor,
static_cast<int>(std::round(static_cast<double>(width) / factor)) * factor);
resize_image_dims(height, width, h_bar, w_bar, factor, min_pixels, max_pixels, resize_mode);
LOG_DEBUG("resize conditioner ref image %d from %dx%d to %dx%d", i, height, width, h_bar, w_bar);
@@ -2268,30 +2362,33 @@ struct LLMEmbedder : public Conditioner {
min_length = 512 + prompt_template_encode_start_idx;
int image_embed_idx = 36 + 6;
int min_pixels = 384 * 384;
int max_pixels = 560 * 560;
int min_pixels = conditioner_params.ref_image_params.vlm_min_size;
if (min_pixels <= 0) {
min_pixels = 384;
if (resize_mode == RefImageResizeMode::AREA) {
min_pixels *= min_pixels;
}
}
int max_pixels = conditioner_params.ref_image_params.vlm_max_size;
if (max_pixels <= 0) {
max_pixels = 560;
if (resize_mode == RefImageResizeMode::AREA) {
max_pixels *= max_pixels;
}
}
std::string placeholder = "<|image_pad|>";
std::string img_prompt;
for (int i = 0; i < conditioner_params.ref_images->size(); i++) {
const auto& image = (*conditioner_params.ref_images)[i];
double factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
const int factor = llm->config.vision.patch_size * llm->config.vision.spatial_merge_size;
int height = static_cast<int>(image.shape()[1]);
int width = static_cast<int>(image.shape()[0]);
int h_bar = static_cast<int>(std::round(height / factor) * factor);
int w_bar = static_cast<int>(std::round(width / factor) * factor);
int h_bar = static_cast<int>(std::round(static_cast<double>(height) / factor) * factor);
int w_bar = static_cast<int>(std::round(static_cast<double>(width) / factor) * factor);
if (static_cast<double>(h_bar) * w_bar > max_pixels) {
double beta = std::sqrt((height * width) / static_cast<double>(max_pixels));
h_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(height / beta / factor)) * static_cast<int>(factor));
w_bar = std::max(static_cast<int>(factor),
static_cast<int>(std::floor(width / beta / factor)) * static_cast<int>(factor));
} else if (static_cast<double>(h_bar) * w_bar < min_pixels) {
double beta = std::sqrt(static_cast<double>(min_pixels) / (height * width));
h_bar = static_cast<int>(std::ceil(height * beta / factor)) * static_cast<int>(factor);
w_bar = static_cast<int>(std::ceil(width * beta / factor)) * static_cast<int>(factor);
}
resize_image_dims(height, width, h_bar, w_bar, factor, min_pixels, max_pixels, resize_mode);
LOG_DEBUG("resize conditioner ref image %d from %dx%d to %dx%d", i, height, width, h_bar, w_bar);