feat: support for SDXS-512 model #1180
Conversation
stable-diffusion.cpp
Outdated
| std::shared_ptr<TinyAutoEncoder> first_stage_model_tiny = nullptr; | ||
| std::shared_ptr<TinyAutoEncoder> tae_first_stage; |
There was a problem hiding this comment.
Why not just use tae_first_stage ?
There was a problem hiding this comment.
Also even though it's recommended to use with TAESD by default, it should work just fine with sd1.x KL-F8 VAE, just slower.
|
@stduhpf wrote:
Yes, but one needs additional options, it is slower and the output is not in the same quality as intended by IDkiro. ~/stable-diffusion.cpp/build/bin/sd-cli -m sdxs -p "portrait of a lovely cat" \
--cfg-scale 1 --steps 1 --taesd sdxs/vae/diffusion_pytorch_model.safetensorsI simply like the idea of using the provided models just "out of the box" without more mandatory options than really needed. That was the reason to continue after the second commit (i.e. the U-Net part). Anyway, a big THANK YOU for code your revision. |
|
Could you provide sdxs.safetensors for testing? |
|
..and here it is: use it via |
3 participants
Once I wrote "three TinySD models should be enough" ( #939 ), but I changed my mind on user's request in December 2025 ( #603 ) and because SDXS-512 is so incredible fast. (That makes SDXS very handy for my sdcpp-on-android project.)
The main challenge for me was that SDXS does not use AutoEncoderKL as primary VAE (as most else) but AutoEncoderTiny, see also https://huggingface.co/IDKiro/sdxs-512-dreamshaper . I also hope that including SDXS into sd.cpp will convince @IDKiro to release into the public his SDXS-1024 one day.