Tags: thomasbergersen/stable-diffusion.cpp
Tags
sync: update ggml to fix large image generation with SYCL backend (le… …ejet#380) * turn off fast-math on host in SYCL backend Signed-off-by: zhentaoyu <[email protected]> * update ggml for sync some sycl ops Signed-off-by: zhentaoyu <[email protected]> * update sycl readme and ggml Signed-off-by: zhentaoyu <[email protected]> --------- Signed-off-by: zhentaoyu <[email protected]>
fix: improve VAE tiling (leejet#372) * fix and improve: VAE tiling - properly handle the upper left corner interpolating both x and y - refactor out lerp - use smootherstep to preserve more detail and spend less area blending * actually fix vae tile merging Co-authored-by: stduhpf <[email protected]> * remove the now unused lerp function --------- Co-authored-by: stduhpf <[email protected]>
feat: add exponential scheduler (leejet#346) * feat: added exponential scheduler * updated README * improved exponential formatting --------- Co-authored-by: leejet <[email protected]>
feat: add vulkan backend support (leejet#291) * Fix includes and init vulkan the same as llama.cpp * Add Windows Vulkan CI * Updated ggml submodule * support epsilon as a parameter for ggml_group_norm --------- Co-authored-by: Cloudwalk <[email protected]> Co-authored-by: Oleg Skutte <[email protected]> Co-authored-by: leejet <[email protected]>
PreviousNext