DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 03:24:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: return generation metadata with core results (#2206)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-25 03:18:03 +08:00
1 parent b29cad540a
commit a85db96aa5
37 files changed
+1528 -758
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/pipeline/request.cpp
+82 -19
View File
@@ -1,4 +1,5 @@
#include "request.h"
#include "conditioning/conditioner.hpp"
#include <algorithm>
#include <cmath>
@@ -6,6 +7,8 @@
#include <ctime>
#include "diffusion_engine.h"
#include "generation.h"
#include "model/vae/vae.hpp"
#include "model_definition.h"
#include "runtime/denoiser.hpp"
@@ -66,7 +69,7 @@ namespace sd::pipeline {
return DISCRETE_SCHEDULER;
}
static int64_t resolve_seed(int64_t seed) {
int64_t resolve_seed(int64_t seed) {
if (seed >= 0) {
return seed;
}
@@ -127,6 +130,7 @@ namespace sd::pipeline {
seed = sd_img_gen_params->seed;
batch_count = sd_img_gen_params->batch_count;
qwen_image_layers = std::max(0, sd_img_gen_params->qwen_image_layers);
is_layered_image = sd->version == VERSION_QWEN_IMAGE_LAYERED;
clip_skip = sd_img_gen_params->clip_skip;
shifted_timestep = sd_img_gen_params->sample_params.shifted_timestep;
strength = sd_img_gen_params->strength;
@@ -137,8 +141,18 @@ namespace sd::pipeline {
pm_params = sd_img_gen_params->pm_params;
pulid_params = sd_img_gen_params->pulid_params;
hires = sd_img_gen_params->hires;
vae_tiling_params = sd_img_gen_params->vae_tiling_params;
cache_params = &sd_img_gen_params->cache;
sample_params = sd_img_gen_params->sample_params;
resolve(sd);
if (!sd_img_gen_params->control_image.data)
models.erase("control_net");
if (!sd_img_gen_params->ip_adapter_image.data)
models.erase("ip_adapter");
if (!pm_params.id_images || pm_params.id_images_count <= 0)
models.erase("photo_maker");
if (!pulid_params.id_embedding_path || !*pulid_params.id_embedding_path)
models.erase("pulid_weights");
}
GenerationRequest::GenerationRequest(StableDiffusionGGML* sd, const sd_vid_gen_params_t* sd_vid_gen_params) {
@@ -166,7 +180,20 @@ namespace sd::pipeline {
guidance = sd_vid_gen_params->sample_params.guidance;
high_noise_guidance = sd_vid_gen_params->high_noise_sample_params.guidance;
hires = sd_vid_gen_params->hires;
vae_tiling_params = sd_vid_gen_params->vae_tiling_params;
sample_params = sd_vid_gen_params->sample_params;
high_noise_sample_params = sd_vid_gen_params->high_noise_sample_params;
use_high_noise = sd->high_noise_diffusion_model != nullptr;
use_vace = sd->diffusion_model && (sd->diffusion_model->get_desc() == "Wan2.1-VACE-1.3B" ||
sd->diffusion_model->get_desc() == "Wan2.x-VACE-14B");
shifted_timestep = sample_params.shifted_timestep;
if (sd->config_ && sd->config_->animatediff_loaded && sd_version_supports_animatediff(sd->version))
frames = std::min(requested_frames, 32);
resolve(sd);
models.erase("control_net");
models.erase("ip_adapter");
models.erase("photo_maker");
models.erase("pulid_weights");
if (frames != requested_frames) {
LOG_WARN("align video frames from %d to %d for %s",
requested_frames,
@@ -201,6 +228,10 @@ namespace sd::pipeline {
spatial_multiple);
}
int64_t GenerationRequest::seed_for_batch(int index) const {
return static_cast<int64_t>((static_cast<uint64_t>(seed) + index) & INT64_MAX);
}
void GenerationRequest::resolve_hires() {
if (!hires.enabled) {
return;
@@ -307,6 +338,23 @@ namespace sd::pipeline {
}
void GenerationRequest::resolve(StableDiffusionGGML* sd) {
if (sd->config_) {
models = sd->config_->models;
if (!use_high_noise)
models.erase("high_noise_diffusion_model");
if (!sd->clip_vision)
models.erase("clip_vision");
if (!sd->audio_vae_model || frames <= 0)
models.erase("audio_vae");
if (!sd->audio_encoder || frames <= 0)
models.erase("audio_encoder");
if (!sd->config_->animatediff_loaded || !sd_version_supports_animatediff(sd->version) || frames <= 0)
models.erase("motion_module");
if (sd->uses_tae() && !sd->tae_preview_only())
models.erase("vae");
else
models.erase("taesd");
}
if (sd_version_is_minit2i(sd->version) && (width != 512 || height != 512)) {
width = 512;
height = 512;
@@ -314,7 +362,11 @@ namespace sd::pipeline {
}
align_generation_request_size();
resolve_hires();
if (sd->first_stage_model)
vae_tiling_params = sd->first_stage_model->resolve_tiling_params(vae_tiling_params);
seed = resolve_seed(seed);
if (sd->cond_stage_model)
clip_skip = sd->cond_stage_model->resolve_clip_skip(clip_skip);
resolve_guidance(sd, &guidance, &use_uncond, &use_img_uncond, has_ref_images);
if (sd->high_noise_diffusion_model) {
@@ -330,33 +382,44 @@ namespace sd::pipeline {
LOG_WARN("timestep shifting is only supported for SDXL models!");
shifted_timestep = 0;
}
sample_params.guidance = guidance;
sample_params.shifted_timestep = shifted_timestep;
sample_params.sample_method = resolve_sample_method(sd, sample_params.sample_method);
sample_params.scheduler = resolve_scheduler(sd, sample_params.scheduler, sample_params.sample_method);
sample_params.eta = resolve_eta(sd, sample_params.eta, sample_params.sample_method);
if (frames > 0) {
high_noise_sample_params.guidance = high_noise_guidance;
high_noise_sample_params.sample_method = resolve_sample_method(sd, high_noise_sample_params.sample_method);
high_noise_sample_params.scheduler = resolve_scheduler(sd, high_noise_sample_params.scheduler, high_noise_sample_params.sample_method);
high_noise_sample_params.eta = resolve_eta(sd, high_noise_sample_params.eta, high_noise_sample_params.sample_method);
}
}
SamplePlan::SamplePlan(StableDiffusionGGML* sd,
const sd_img_gen_params_t* sd_img_gen_params,
const GenerationRequest& request) {
sample_method = sd_img_gen_params->sample_params.sample_method;
extra_sample_args = sd_img_gen_params->sample_params.extra_sample_args;
eta = sd_img_gen_params->sample_params.eta;
sample_steps = sd_img_gen_params->sample_params.sample_steps;
resolve(sd, &request, &sd_img_gen_params->sample_params);
sample_method = request.sample_params.sample_method;
extra_sample_args = request.sample_params.extra_sample_args;
eta = request.sample_params.eta;
sample_steps = request.sample_params.sample_steps;
resolve(sd, &request, &request.sample_params);
}
SamplePlan::SamplePlan(StableDiffusionGGML* sd,
const sd_vid_gen_params_t* sd_vid_gen_params,
const GenerationRequest& request) {
sample_method = sd_vid_gen_params->sample_params.sample_method;
extra_sample_args = sd_vid_gen_params->sample_params.extra_sample_args;
eta = sd_vid_gen_params->sample_params.eta;
sample_steps = sd_vid_gen_params->sample_params.sample_steps;
sample_method = request.sample_params.sample_method;
extra_sample_args = request.sample_params.extra_sample_args;
eta = request.sample_params.eta;
sample_steps = request.sample_params.sample_steps;
if (sd->high_noise_diffusion_model) {
high_noise_sample_steps = sd_vid_gen_params->high_noise_sample_params.sample_steps;
high_noise_sample_method = sd_vid_gen_params->high_noise_sample_params.sample_method;
high_noise_extra_sample_args = sd_vid_gen_params->high_noise_sample_params.extra_sample_args;
high_noise_eta = sd_vid_gen_params->high_noise_sample_params.eta;
high_noise_sample_steps = request.high_noise_sample_params.sample_steps;
high_noise_sample_method = request.high_noise_sample_params.sample_method;
high_noise_extra_sample_args = request.high_noise_sample_params.extra_sample_args;
high_noise_eta = request.high_noise_sample_params.eta;
}
moe_boundary = sd_vid_gen_params->moe_boundary;
resolve(sd, &request, &sd_vid_gen_params->sample_params);
resolve(sd, &request, &request.sample_params);
}
void SamplePlan::resolve(StableDiffusionGGML* sd,
@@ -382,10 +445,10 @@ namespace sd::pipeline {
}
}
} else {
scheduler_t scheduler = resolve_scheduler(sd,
sample_params->scheduler,
sample_method);
int sample_seq_len = sd->get_image_seq_len(request->height, request->width);
scheduler = resolve_scheduler(sd,
sample_params->scheduler,
sample_method);
int sample_seq_len = sd->get_image_seq_len(request->height, request->width);
if (sd_version_is_ltxav(sd->version) && request->frames > 0) {
int latent_frames = ((request->frames - 1) / 8) + 1;
sample_seq_len *= latent_frames;