AUTOMATIC1111/stable-diffusion-webui · error · Exception

Could not find checkpoint with name {self.hr_checkpoint_name

Error message

Could not find checkpoint with name {self.hr_checkpoint_name}

What it means

In StableDiffusionProcessingTxt2Img.init for hires-fix: when hr_checkpoint_name is set to something other than 'Use same checkpoint', it is resolved with sd_models.get_closet_checkpoint_match; None means no known checkpoint matches, and the Exception aborts before the first pass. It protects the second (hires) pass from running with an unloadable model.

Source

Thrown at modules/processing.py:1260

                if src_ratio < dst_ratio:
                    self.hr_upscale_to_x = self.hr_resize_x
                    self.hr_upscale_to_y = self.hr_resize_x * self.height // self.width
                else:
                    self.hr_upscale_to_x = self.hr_resize_y * self.width // self.height
                    self.hr_upscale_to_y = self.hr_resize_y

                self.truncate_x = (self.hr_upscale_to_x - target_w) // opt_f
                self.truncate_y = (self.hr_upscale_to_y - target_h) // opt_f

    def init(self, all_prompts, all_seeds, all_subseeds):
        if self.enable_hr:
            self.extra_generation_params["Denoising strength"] = self.denoising_strength

            if self.hr_checkpoint_name and self.hr_checkpoint_name != 'Use same checkpoint':
                self.hr_checkpoint_info = sd_models.get_closet_checkpoint_match(self.hr_checkpoint_name)

                if self.hr_checkpoint_info is None:
                    raise Exception(f'Could not find checkpoint with name {self.hr_checkpoint_name}')

                self.extra_generation_params["Hires checkpoint"] = self.hr_checkpoint_info.short_title

            if self.hr_sampler_name is not None and self.hr_sampler_name != self.sampler_name:
                self.extra_generation_params["Hires sampler"] = self.hr_sampler_name

            def get_hr_prompt(p, index, prompt_text, **kwargs):
                hr_prompt = p.all_hr_prompts[index]
                return hr_prompt if hr_prompt != prompt_text else None

            def get_hr_negative_prompt(p, index, negative_prompt, **kwargs):
                hr_negative_prompt = p.all_hr_negative_prompts[index]
                return hr_negative_prompt if hr_negative_prompt != negative_prompt else None

            self.extra_generation_params["Hires prompt"] = get_hr_prompt
            self.extra_generation_params["Hires negative prompt"] = get_hr_negative_prompt

            self.extra_generation_params["Hires schedule type"] = None  # to be set in sd_samplers_kdiffusion.py

View on GitHub (pinned to 82a973c043)

Solutions

1. Restore the checkpoint file referenced by hr_checkpoint_name and refresh the model list.
2. Or set the dropdown/'hr_checkpoint_name' back to 'Use same checkpoint' so hires fix reuses the primary model.
3. Verify the exact checkpoint title via the API (sdapi/v1/sd-models) and use a matching substring.

Example fix

# before
payload['hr_checkpoint_name'] = 'myDeletedModel.safetensors'  # Exception

# after
payload['hr_checkpoint_name'] = 'Use same checkpoint'

from modules import sd_models

def validate_hr_checkpoint(name):
    if not name or name == 'Use same checkpoint':
        return True
    return sd_models.get_closet_checkpoint_match(name) is not None

if not validate_hr_checkpoint(payload.get('hr_checkpoint_name')):
    payload['hr_checkpoint_name'] = 'Use same checkpoint'

def hires_checkpoint_ok(name: str) -> bool:
    return (not name) or name == 'Use same checkpoint' or sd_models.get_closet_checkpoint_match(name) is not None

try:
    processed = process_images(p)
except Exception as e:
    if 'Could not find checkpoint' in str(e) and getattr(p, 'hr_checkpoint_name', None):
        p.hr_checkpoint_name = 'Use same checkpoint'
        processed = process_images(p)
    else:
        raise

When it happens

Trigger: Enabling hires fix with 'Hires checkpoint' set to a name that matches no checkpoint in models/Stable-diffusion — deleted file, typo, or a saved UI state referencing a model not present on this machine.

Common situations: Moving a webui install to another machine without copying all checkpoints; renaming model files while the dropdown retains the old title; API scripts hardcoding a hires checkpoint name.

Related errors

• Could not find checkpoint with name {p.refiner_checkpoint}
• could not find upscaler named {self.hr_upscaler}
• When merging inpainting model with a normal one, A must be t
• When merging instruct-pix2pix model with a normal one, A mus
• No GFPGAN model found

AI-assisted analysis of AUTOMATIC1111/stable-diffusion-webui@82a973c043 (2026-08-14). Data as JSON: /api/errors/321401ce567dc173. Report an issue: GitHub.