mrq/stable-diffusion-webui
1
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

--opt-split-attention now on by default for torch.cuda, off for others (cpu and MPS; because the option does not work there according to reports)

Browse Source
This commit is contained in:
AUTOMATIC 2022-09-21 09:49:02 +03:00
parent 6785fabefb
commit 254da5d127
2 changed files with 3 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
modules/sd_hijack.py
View File

@ -245,7 +245,7 @@ class StableDiffusionModelHijack:
if cmd_opts.opt_split_attention_v1: if cmd_opts.opt_split_attention_v1:
ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward_v1 ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward_v1
elif not cmd_opts.disable_opt_split_attention: elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward ldm.modules.attention.CrossAttention.forward = split_cross_attention_forward
ldm.modules.diffusionmodules.model.nonlinearity = nonlinearity_hijack ldm.modules.diffusionmodules.model.nonlinearity = nonlinearity_hijack
ldm.modules.diffusionmodules.model.AttnBlock.forward = cross_attention_attnblock_forward ldm.modules.diffusionmodules.model.AttnBlock.forward = cross_attention_attnblock_forward

7
modules/shared.py
View File

@ -36,8 +36,8 @@ parser.add_argument("--precision", type=str, help="evaluate at this precision",
parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)") parser.add_argument("--share", action='store_true', help="use share=True for gradio and make the UI accessible through their site (doesn't work for me but you might have better luck)")
parser.add_argument("--esrgan-models-path", type=str, help="path to directory with ESRGAN models", default=os.path.join(script_path, 'ESRGAN')) parser.add_argument("--esrgan-models-path", type=str, help="path to directory with ESRGAN models", default=os.path.join(script_path, 'ESRGAN'))
parser.add_argument("--swinir-models-path", type=str, help="path to directory with SwinIR models", default=os.path.join(script_path, 'SwinIR')) parser.add_argument("--swinir-models-path", type=str, help="path to directory with SwinIR models", default=os.path.join(script_path, 'SwinIR'))
parser.add_argument("--opt-split-attention", action='store_true', help="does not do anything") parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")
parser.add_argument("--disable-opt-split-attention", action='store_true', help="disable an optimization that reduces vram usage by a lot") parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")
parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find") parser.add_argument("--opt-split-attention-v1", action='store_true', help="enable older version of split attention optimization that does not consume all the VRAM it can find")
parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests") parser.add_argument("--listen", action='store_true', help="launch gradio with 0.0.0.0 as server name, allowing to respond to network requests")
parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None) parser.add_argument("--port", type=int, help="launch gradio with given server port, you need root/admin rights for ports < 1024, defaults to 7860 if available", default=None)
@ -54,9 +54,6 @@ parser.add_argument("--use-textbox-seed", action='store_true', help="use textbox
cmd_opts = parser.parse_args() cmd_opts = parser.parse_args()
if cmd_opts.opt_split_attention:
print("Information: --opt-split-attention is now the default. To remove this message, remove --opt-split-attention from command line arguments. To disable the optimization, use --disable-opt-split-attention")
device = get_optimal_device() device = get_optimal_device()
batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram) batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)