[GH-ISSUE #10] TypeError: must be real number, not NoneType #7

New issue

Open

opened 2026-10-30 21:03:07 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-30 21:03:07 +00:00

Owner

Originally created by @HyunJae5463 on GitHub (Aug 24, 2023).
Original GitHub issue: https://github.com/ahgsql/StyleSelectorXL/issues/10

Getting this error when i select a style when i use HighRes Fix.

    Traceback (most recent call last):
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\call_queue.py", line 58, in f
        res = list(func(*args, **kwargs))
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f
        res = func(*args, **kwargs)
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\txt2img.py", line 69, in txt2img
        processed = processing.process_images(p)
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 680, in process_images
        res = process_images_inner(p)
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 786, in process_images_inner
        p.setup_conds()
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 1207, in setup_conds
        self.calculate_hr_conds()
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 1190, in calculate_hr_conds
        self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.hr_negative_prompts, self.steps * self.step_multiplier, [self.cached_hr_uc, self.cached_uc], self.hr_extra_network_data)
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 353, in get_conds_with_caching
        cache[1] = function(shared.sd_model, required_prompts, steps)
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\prompt_parser.py", line 163, in get_learned_conditioning
        conds = model.get_learned_conditioning(texts)
      File "C:\AI\XL\stable-diffusion-webui-directml\modules\sd_models_xl.py", line 24, 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

Originally created by @HyunJae5463 on GitHub (Aug 24, 2023). Original GitHub issue: https://github.com/ahgsql/StyleSelectorXL/issues/10 Getting this error when i select a style when i use HighRes Fix. ``` Traceback (most recent call last): File "C:\AI\XL\stable-diffusion-webui-directml\modules\call_queue.py", line 58, in f res = list(func(*args, **kwargs)) File "C:\AI\XL\stable-diffusion-webui-directml\modules\call_queue.py", line 37, in f res = func(*args, **kwargs) File "C:\AI\XL\stable-diffusion-webui-directml\modules\txt2img.py", line 69, in txt2img processed = processing.process_images(p) File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 680, in process_images res = process_images_inner(p) File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 786, in process_images_inner p.setup_conds() File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 1207, in setup_conds self.calculate_hr_conds() File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 1190, in calculate_hr_conds self.hr_uc = self.get_conds_with_caching(prompt_parser.get_learned_conditioning, self.hr_negative_prompts, self.steps * self.step_multiplier, [self.cached_hr_uc, self.cached_uc], self.hr_extra_network_data) File "C:\AI\XL\stable-diffusion-webui-directml\modules\processing.py", line 353, in get_conds_with_caching cache[1] = function(shared.sd_model, required_prompts, steps) File "C:\AI\XL\stable-diffusion-webui-directml\modules\prompt_parser.py", line 163, in get_learned_conditioning conds = model.get_learned_conditioning(texts) File "C:\AI\XL\stable-diffusion-webui-directml\modules\sd_models_xl.py", line 24, 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 ```

bsakaguchi referenced this issue

2026-10-30 21:03:27 +00:00

[PR #13] for all styles each batch will have the same style #33