ditch --always-batch-cond-uncond in favor of an UI setting

modules/cmd_args.py

@@ -37,7 +37,7 @@ parser.add_argument("--allow-code", action='store_true', help="allow custom scri
 parser.add_argument("--medvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a little speed for low VRM usage")
 parser.add_argument("--lowvram", action='store_true', help="enable stable diffusion model optimizations for sacrificing a lot of speed for very low VRM usage")
 parser.add_argument("--lowram", action='store_true', help="load stable diffusion checkpoint weights to VRAM instead of RAM")
-parser.add_argument("--always-batch-cond-uncond", action='store_true', help="disables cond/uncond batching that is enabled to save memory with --medvram or --lowvram")
+parser.add_argument("--always-batch-cond-uncond", action='store_true', help="does not do anything")
 parser.add_argument("--unload-gfpgan", action='store_true', help="does not do anything.")
 parser.add_argument("--precision", type=str, help="evaluate at this precision", choices=["full", "autocast"], default="autocast")
 parser.add_argument("--upcast-sampling", action='store_true', help="upcast sampling. No effect with --no-half. Usually produces similar results to --no-half with better performance while using less memory.")

modules/sd_samplers_cfg_denoiser.py

@@ -165,7 +165,7 @@ class CFGDenoiser(torch.nn.Module):
             else:
                 cond_in = catenate_conds([tensor, uncond])
 
-            if shared.batch_cond_uncond:
+            if shared.opts.batch_cond_uncond:
                 x_out = self.inner_model(x_in, sigma_in, cond=make_condition_dict(cond_in, image_cond_in))
             else:
                 x_out = torch.zeros_like(x_in)
@@ -175,7 +175,7 @@ class CFGDenoiser(torch.nn.Module):
                     x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond=make_condition_dict(subscript_cond(cond_in, a, b), image_cond_in[a:b]))
         else:
             x_out = torch.zeros_like(x_in)
-            batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
+            batch_size = batch_size*2 if shared.opts.batch_cond_uncond else batch_size
             for batch_offset in range(0, tensor.shape[0], batch_size):
                 a = batch_offset
                 b = min(a + batch_size, tensor.shape[0])

modules/shared.py

@@ -10,7 +10,7 @@ from modules import util
 cmd_opts = shared_cmd_options.cmd_opts
 parser = shared_cmd_options.parser
 
-batch_cond_uncond = cmd_opts.always_batch_cond_uncond or not (cmd_opts.lowvram or cmd_opts.medvram)
+batch_cond_uncond = True  # old field, unused now in favor of shared.opts.batch_cond_uncond
 parallel_processing_allowed = not cmd_opts.lowvram and not cmd_opts.medvram
 styles_filename = cmd_opts.styles_file
 config_filename = cmd_opts.ui_settings_file

modules/shared_options.py

@@ -192,7 +192,8 @@ options_templates.update(options_section(('optimizations', "Optimizations"), {
     "token_merging_ratio_img2img": OptionInfo(0.0, "Token merging ratio for img2img", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}).info("only applies if non-zero and overrides above"),
     "token_merging_ratio_hr": OptionInfo(0.0, "Token merging ratio for high-res pass", gr.Slider, {"minimum": 0.0, "maximum": 0.9, "step": 0.1}, infotext='Token merging ratio hr').info("only applies if non-zero and overrides above"),
     "pad_cond_uncond": OptionInfo(False, "Pad prompt/negative prompt to be same length", infotext='Pad conds').info("improves performance when prompt and negative prompt have different lengths; changes seeds"),
-    "persistent_cond_cache": OptionInfo(True, "Persistent cond cache").info("Do not recalculate conds from prompts if prompts have not changed since previous calculation"),
+    "persistent_cond_cache": OptionInfo(True, "Persistent cond cache").info("do not recalculate conds from prompts if prompts have not changed since previous calculation"),
+    "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"),
 }))
 
 options_templates.update(options_section(('compatibility', "Compatibility"), {