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: add Fibo 2.0 Dev and Edit Turbo support (#2180)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-21 23:32:19 +08:00
1 parent 939895f00e
commit 2e2ba3faec
22 files changed
+931 -69
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/pipeline/image.cpp
+21 -13
View File
@@ -284,26 +284,34 @@ namespace sd::pipeline {
LOG_VERBOSE("auto resize ref images");
double vae_width;
double vae_height;
if (ref_image_params.resize_vae_to_target) {
int factor = sd_version_is_qwen_image(sd->version) ? 32 : 16;
if (ref_image_params.resize_vae_to_target || (ref_image_params.resize_single_ref_to_target && ref_images.size() == 1)) {
vae_width = request->width;
vae_height = request->height;
} else {
int default_pixels = sd->version == VERSION_QWEN_IMAGE_2_1 ? request->width * request->height : 1024 * 1024;
int target_pixels = ref_image_params.vae_input_max_pixels > 0 ? ref_image_params.vae_input_max_pixels : default_pixels;
int vae_image_size = std::min(target_pixels, request->width * request->height);
vae_width = sqrt(vae_image_size * ref_images[i].shape()[0] / ref_images[i].shape()[1]);
vae_height = vae_width * ref_images[i].shape()[1] / ref_images[i].shape()[0];
if (ref_image_params.vae_size_buckets) {
auto size = sd::select_image_size_bucket(static_cast<int>(ref_images[i].shape()[0]), static_cast<int>(ref_images[i].shape()[1]), target_pixels, factor, request->width, request->height);
vae_width = size.first;
vae_height = size.second;
} else {
int vae_image_size = std::min(target_pixels, request->width * request->height);
vae_width = sqrt(vae_image_size * ref_images[i].shape()[0] / ref_images[i].shape()[1]);
vae_height = vae_width * ref_images[i].shape()[1] / ref_images[i].shape()[0];
}
}
int factor = sd_version_is_qwen_image(sd->version) ? 32 : 16;
vae_height = round(vae_height / factor) * factor;
vae_width = round(vae_width / factor) * factor;
auto resized_ref_img = sd::ops::interpolate(ref_images[i],
{static_cast<int>(vae_width),
static_cast<int>(vae_height),
ref_images[i].shape()[2],
ref_images[i].shape()[3]});
auto resized_ref_img = ref_image_params.vae_center_crop
? sd::resize_and_center_crop(ref_images[i], static_cast<int>(vae_width), static_cast<int>(vae_height))
: sd::ops::interpolate(ref_images[i],
{static_cast<int>(vae_width),
static_cast<int>(vae_height),
ref_images[i].shape()[2],
ref_images[i].shape()[3]});
LOG_VERBOSE("resize vae ref image %d from %" PRId64 "x%" PRId64 " to %" PRId64 "x%" PRId64,
static_cast<int>(i),
@@ -313,7 +321,7 @@ namespace sd::pipeline {
resized_ref_img.shape()[0]);
ref_latent = sd->encode_first_stage(resized_ref_img);
if (sd->version == VERSION_QWEN_IMAGE_2_1) {
if (ref_image_params.vlm_use_vae_input) {
ref_images[i] = std::move(resized_ref_img);
}
} else {
@@ -482,8 +490,8 @@ namespace sd::pipeline {
}
condition_params.text = request->negative_prompt;
condition_params.zero_out_masked = zero_out_masked;
if (sd_version_is_llada_image(sd->version)) {
// LLaDA-Image CFG keeps the source latent but drops its SigVQ features.
if (sd_version_is_llada_image(sd->version) || sd->version == VERSION_FIBO2) {
// Keep source latents in CFG, but omit source images from the text encoder.
condition_params.ref_images = nullptr;
}
uncond = sd->get_learned_condition(condition_params);