High-fidelity FP8 quantization for diffusion models (SDXL). HSWQ uses
sensitivity
and
importance
analysis instead of naive uniform cast, and offers two modes: standard-compatible (V1) and high-performance scaled (V2).
We extend our deepest respect and gratitude to the
Nunchaku Team
for their groundbreaking work on SVDQ quantization and for sharing their models with the community. This collection relies heavily on their research and original implementation.
HSWQ-fp8-SDXL huggingface.co is an AI model on huggingface.co that provides HSWQ-fp8-SDXL's model effect (), which can be used instantly with this ApacheOne HSWQ-fp8-SDXL model. huggingface.co supports a free trial of the HSWQ-fp8-SDXL model, and also provides paid use of the HSWQ-fp8-SDXL. Support call HSWQ-fp8-SDXL model through api, including Node.js, Python, http.
HSWQ-fp8-SDXL huggingface.co is an online trial and call api platform, which integrates HSWQ-fp8-SDXL's modeling effects, including api services, and provides a free online trial of HSWQ-fp8-SDXL, you can try HSWQ-fp8-SDXL online for free by clicking the link below.
ApacheOne HSWQ-fp8-SDXL online free url in huggingface.co:
HSWQ-fp8-SDXL is an open source model from GitHub that offers a free installation service, and any user can find HSWQ-fp8-SDXL on GitHub to install. At the same time, huggingface.co provides the effect of HSWQ-fp8-SDXL install, users can directly use HSWQ-fp8-SDXL installed effect in huggingface.co for debugging and trial. It also supports api for free installation.