DarthAffe/stable-diffusion.cpp
1
0
Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-09-24 20:20:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: preserve alpha when upscaling RGBA images with ESRGAN (#2029)

Browse Source
This commit is contained in:
leejet 2026-09-23 02:23:10 +08:00 committed by GitHub
parent 28b454bda1
commit c92d73c408
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 24 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/esrgan.md
View File

@ -2,6 +2,8 @@
You can use ESRGAN—such as the model [RealESRGAN_x4plus_anime_6B.pth](https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth)—to upscale the generated images and improve their overall resolution and clarity.
RGBA images, including Qwen Image 2.1 output, keep their alpha channel during model upscaling and hires fix. ESRGAN processes the RGB channels; the alpha channel is resized with bilinear interpolation and recombined with the upscaled image.
- Specify the model path using the `--upscale-model PATH` parameter. example:
```bash

24
src/upscaler.cpp
View File

@ -111,10 +111,22 @@ bool UpscalerGGML::load_from_file(const std::string& esrgan_path,
sd::Tensor<float> UpscalerGGML::upscale_tensor(const sd::Tensor<float>& input_tensor) {
sd::ParallelScope tensor_scope(&tensor_executor);
if (input_tensor.empty() || input_tensor.dim() != 4 ||
(input_tensor.shape()[2] != 3 && input_tensor.shape()[2] != 4)) {
LOG_ERROR("esrgan expects a 4D RGB or RGBA image tensor");
return {};
}
const bool has_alpha = input_tensor.shape()[2] == 4;
sd::Tensor<float> rgb;
if (has_alpha) {
rgb = sd::ops::slice(input_tensor, 2, 0, 3);
}
const sd::Tensor<float>& model_input = has_alpha ? rgb : input_tensor;
sd::Tensor<float> upscaled;
const int scale = esrgan_upscaler->config.scale;
if (tile_size <= 0 || (input_tensor.shape()[0] <= tile_size && input_tensor.shape()[1] <= tile_size)) {
upscaled = esrgan_upscaler->compute(n_threads, input_tensor);
upscaled = esrgan_upscaler->compute(n_threads, model_input);
} else {
auto on_processing = [&](const sd::Tensor<float>& input_tile) -> sd::Tensor<float> {
auto output_tile = esrgan_upscaler->compute(n_threads, input_tile);
@ -125,7 +137,7 @@ sd::Tensor<float> UpscalerGGML::upscale_tensor(const sd::Tensor<float>& input_te
return output_tile;
};
upscaled = process_tiles_2d(input_tensor,
upscaled = process_tiles_2d(model_input,
static_cast<int>(input_tensor.shape()[0] * scale),
static_cast<int>(input_tensor.shape()[1] * scale),
scale,
@ -141,6 +153,14 @@ sd::Tensor<float> UpscalerGGML::upscale_tensor(const sd::Tensor<float>& input_te
LOG_ERROR("esrgan compute failed");
return {};
}
if (has_alpha) {
auto alpha = sd::ops::slice(input_tensor, 2, 3, 4);
auto alpha_shape = alpha.shape();
alpha_shape[0] = upscaled.shape()[0];
alpha_shape[1] = upscaled.shape()[1];
alpha = sd::ops::interpolate(alpha, alpha_shape, sd::ops::InterpolateMode::Bilinear);
upscaled = sd::ops::concat(upscaled, alpha, 2);
}
return upscaled;
}