Package sd-cpp: Information

Source package: sd-cpp
Version: 20251122-alt1
Latest version according to Repology
Build time:  Nov 28, 2025, 07:00 AM in the task #401248
Report package bug
License: MIT
Summary: Diffusion model (SD, Flux, Wan, Qwen Image) inference in pure C/C++
Description: 
Inference of Diffusion models in pure C/C++. Supports CPU and CUDA.

Supported models:
  Image Models: SD1.x, SD2.x, SD-Turbo, SDXL, SDXL-Turbo, some SD1.x and SDXL
    distilled models, SD3/SD3.5, Flux-dev/Flux-schnell, Chroma,
    Chroma1-Radiance, Qwen Image
  Image Edit Models: FLUX.1-Kontext-dev, Qwen Image Edit/Qwen Image Edit 2509
  Video Models: Wan2.1/Wan2.2
  PhotoMaker support
  Control Net support with SD 1.5
  LoRA support, same as stable-diffusion-webui
  Latent Consistency Models support (LCM/LCM-LoRA)
  Faster and memory efficient latent decoding with TAESD
  Upscale images generated with ESRGAN

Package note: on x86 only x86-64-v3 (with AVX2) is supported.

List of RPM packages built from this SRPM:
sd-cpp (x86_64, aarch64)
sd-cpp-debuginfo (x86_64, aarch64)

Maintainer: Vitaly Chikunov

List of contributors:
Vitaly Chikunov


    1. cmake
    2. gcc-c++
    3. gcc12-c++
    4. libgomp-devel
    5. nvidia-cuda-devel-static
    6. libstdc++-devel-static
    7. rpm-build-cmake

Last changed


Nov. 28, 2025 Vitaly Chikunov 20251122-alt1
- Update to master-377-2034588 (2025-11-22).
Nov. 9, 2025 Vitaly Chikunov 20251107-alt1
- Update to master-350-c2d8ffc (2025-11-07).
- Added Qwen-Image support.
Oct. 6, 2025 Vitaly Chikunov 20250925-alt1
- Update to master-309-35843c7 (2025-09-25).