DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-11 19:36:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: define VAE tile dimensions in image pixels (#2059)

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-09-25 18:20:32 +08:00
1 parent 39ada0863b
commit 19bbbca1c7
14 files changed
+298 -174
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/pipeline/diffusion_engine.cpp
+19 -7
View File
@@ -2883,14 +2883,26 @@ sd::Tensor<float> StableDiffusionGGML::decode_first_stage(const sd::Tensor<float
return sd::ops::clamp((x + 1.f) * 0.5f, 0.0f, 1.0f);
}
auto latents = first_stage_model->diffusion_to_vae_latents(x);
auto decoded = first_stage_model->decode(n_threads, latents, vae_tiling_params, decode_video, circular_x, circular_y);
const bool prefer_temporal_tiling = decode_video && first_stage_model->can_temporal_tile_decode();
while (decoded.empty() &&
sd::backend_fit::prepare_vae_decode_retry_tiling(vae_tiling_params, prefer_temporal_tiling,
first_stage_model->last_compute_status())) {
decoded = first_stage_model->decode(n_threads, latents, vae_tiling_params, decode_video, circular_x, circular_y);
auto tiling_params = first_stage_model->resolve_tiling_params(vae_tiling_params);
const bool prefer_temporal_tiling = decode_video && latents.dim() == 5 && latents.shape()[2] > 1 &&
first_stage_model->can_temporal_tile_decode();
for (;;) {
int tile_size_w = static_cast<int>(latents.shape()[0]);
int tile_size_h = static_cast<int>(latents.shape()[1]);
float tile_overlap;
if (tiling_params.enabled &&
!first_stage_model->get_tile_sizes(tile_size_w, tile_size_h, tile_overlap, tiling_params,
latents.shape()[0], latents.shape()[1])) {
return {};
}
auto decoded = first_stage_model->decode(n_threads, latents, tiling_params, decode_video, circular_x, circular_y);
if (!decoded.empty() ||
!sd::backend_fit::prepare_vae_decode_retry_tiling(tiling_params, prefer_temporal_tiling,
first_stage_model->last_compute_status(),
tile_size_w, tile_size_h, first_stage_model->get_scale_factor())) {
return decoded;
}
}
return decoded;
}
sd::Tensor<float> StableDiffusionGGML::normalize_ltx_video_latents(const sd::Tensor<float>& x) {
src/pipeline/image.cpp
+15 -13
View File
@@ -35,19 +35,21 @@ namespace sd::pipeline {
return original_axes;
}
int tile_size_x, tile_size_y;
int tile_size_w, tile_size_h;
float overlap;
int latent_size_x = request.width / request.vae_scale_factor;
int latent_size_y = request.height / request.vae_scale_factor;
sd->first_stage_model->get_tile_sizes(tile_size_x,
tile_size_y,
overlap,
sd_img_gen_params->vae_tiling_params,
latent_size_x,
latent_size_y);
int latent_size_w = request.width / request.vae_scale_factor;
int latent_size_h = request.height / request.vae_scale_factor;
if (!sd->first_stage_model->get_tile_sizes(tile_size_w,
tile_size_h,
overlap,
sd_img_gen_params->vae_tiling_params,
latent_size_w,
latent_size_h)) {
return original_axes;
}
sd->circular_x = sd->circular_x && (tile_size_x >= latent_size_x);
sd->circular_y = sd->circular_y && (tile_size_y >= latent_size_y);
sd->circular_x = sd->circular_x && (tile_size_w >= latent_size_w);
sd->circular_y = sd->circular_y && (tile_size_h >= latent_size_h);
if (sd->first_stage_model) {
sd->first_stage_model->set_circular_axes(sd->circular_x, sd->circular_y);
@@ -56,8 +58,8 @@ namespace sd::pipeline {
sd->preview_vae->set_circular_axes(sd->circular_x, sd->circular_y);
}
sd->circular_x = original_axes.circular_x && (tile_size_x < latent_size_x);
sd->circular_y = original_axes.circular_y && (tile_size_y < latent_size_y);
sd->circular_x = original_axes.circular_x && (tile_size_w < latent_size_w);
sd->circular_y = original_axes.circular_y && (tile_size_h < latent_size_h);
return original_axes;
}