lllyasviel/stable-diffusion-webui-forge
1
0
Fork 0
mirror of https://github.com/lllyasviel/stable-diffusion-webui-forge.git synced 2026-04-29 10:41:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add optimization --cuda-stream

Browse Source 
See also the readme for more details
This commit is contained in:
lllyasviel
2024-02-24 14:00:48 -08:00
committed by GitHub
parent 0f09d98814
commit 434ca2169f
9 changed files with 63 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
modules/shared_options.py
View File

@@ -216,7 +216,6 @@ options_templates.update(options_section(('optimizations', "Optimizations", "sd"
"batch_cond_uncond": OptionInfo(True, "Batch cond/uncond").info("do both conditional and unconditional denoising in one batch; uses a bit more VRAM during sampling, but improves speed; previously this was controlled by --always-batch-cond-uncond comandline argument"),
"fp8_storage": OptionInfo("Disable", "FP8 weight", gr.Radio, {"choices": ["Disable", "Enable for SDXL", "Enable"]}).info("Use FP8 to store Linear/Conv layers' weight. Require pytorch>=2.1.0."),
"cache_fp16_weight": OptionInfo(False, "Cache FP16 weight for LoRA").info("Cache fp16 weight when enabling FP8, will increase the quality of LoRA. Use more system ram."),
"use_non_streamlined_lowvram": OptionInfo(False, "Use non-streamlined low VRAM mode").info("(Requires restart in Forge.) Do not use the streamlined mode for low VRAM cards. For devices that do not support concurrently copy memory between host and device while executing a kernel. Significantly decreases performance."),
}))
options_templates.update(options_section(('compatibility', "Compatibility", "sd"), {