"TypeError: must be real number, not NoneType" when trying to use Region Prompt Control. Using SDXL, in case it matters.

Manchovies commented 10 months ago

*** Error completing request *** Arguments: ('task(zwfjlvs2uko8hna)', <gradio.routes.Request object at 0x0000024666E31990>, 'hyperdetailed photography, minimalist art sculpture, metallic sculpture, product photograph, desktop wallpaper,', '', [], 20, 'DPM++ 2M Karras', 1, 4, 7, 1344, 768, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], 0, True, 'C-Drive-SDXLRefiner1.0-pruned-no-ema.safetensors [9bfca2abbc]', 0.8, -1, False, -1, 0, 0, 0, True, 'MultiDiffusion', False, True, 1024, 1024, 96, 96, 48, 4, 'None', 2, False, 10, 1, 1, 64, False, True, False, False, True, 0, 0, 0.9999999999999997, 0.5991, 'vantablack metallic chrysanthemum flower, with slight accents of color on the bud in the center, on a dark blue and red leather background', '', 'Foreground', 0.2, -1.0, True, 0, 0.575, 1, 0.425, 'vantablack metallic flower stem, slight accents of color near the bottom of the flower stem, on a dark blue and red leather background', '', 'Foreground', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 0.4, 0.4, 0.2, 0.2, '', '', 'Background', 0.2, -1.0, False, 1536, 96, True, True, True, False, False, False, 'positive', 'comma', 0, False, False, 'start', '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, False, False, False, 0, False) {} Traceback (most recent call last): File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\call_queue.py", line 57, in f res = list(func(*args, **kwargs)) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\call_queue.py", line 36, in f res = func(*args, **kwargs) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\txt2img.py", line 110, in txt2img processed = processing.process_images(p) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\processing.py", line 782, in process_images res = process_images_inner(p) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\processing.py", line 944, in process_images_inner samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\processing.py", line 1256, in sample self.sampler = sd_samplers.create_sampler(self.sampler_name, self.sd_model) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\scripts\tilediffusion.py", line 357, in <lambda> sd_samplers.create_sampler = lambda name, model: self.create_sampler_hijack( File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\scripts\tilediffusion.py", line 445, in create_sampler_hijack delegate.init_custom_bbox(bbox_settings, draw_background, causal_layers) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\tile_utils\utils.py", line 249, in wrapper return fn(*args, **kwargs) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\tile_methods\multidiffusion.py", line 42, in init_custom_bbox super().init_custom_bbox(*args) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\tile_utils\utils.py", line 249, in wrapper return fn(*args, **kwargs) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\tile_methods\abstractdiffusion.py", line 226, in init_custom_bbox bbox.cond, bbox.extra_network_data = Condition.get_custom_cond(prompts, bbox.prompt, p.steps, p.styles) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\tile_utils\utils.py", line 123, in get_custom_cond cond = Condition.get_cond(prompts, steps) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\extensions\multidiffusion-upscaler-for-automatic1111\tile_utils\utils.py", line 129, in get_cond cond = prompt_parser.get_multicond_learned_conditioning(shared.sd_model, prompts, steps) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\prompt_parser.py", line 261, in get_multicond_learned_conditioning learned_conditioning = get_learned_conditioning(model, prompt_flat_list, steps, hires_steps, use_old_scheduling) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\prompt_parser.py", line 188, in get_learned_conditioning conds = model.get_learned_conditioning(texts) File "D:\Users\Spencer\Downloads\StabilityMatrix-win-x64\Data\Packages\Stable Diffusion WebUI\modules\sd_models_xl.py", line 25, in get_learned_conditioning "original_size_as_tuple": torch.tensor([height, width], **devices_args).repeat(len(batch), 1), TypeError: must be real number, not NoneType

Happens with or without refiner. I'm on v1.7.0-437-gce168ab5 of Automatic1111. Fresh install of everything. Tried with FP8 and without, because that is something else I've been playing with. Tried with and without Tiled VAE. No luck so far. Any ideas? Happy to try anything you need or provide more info if needed. It's very reproducible on my system. Thanks for the extension btw :)