Carzit / sd-webui-samplers-scheduler-for-v1.6

a samplers scheduler for stable diffusion webui version 1.6.x
MIT License
22 stars 0 forks source link

SDNEXT: AttributeError: module 'modules.sd_samplers_kdiffusion' has no attribute 'CFGDenoiserKDiffusion' #4

Open RGX650 opened 6 months ago

RGX650 commented 6 months ago

Something related? https://github.com/vladmandic/automatic/issues/2044 https://github.com/mcmonkeyprojects/sd-dynamic-thresholding/issues/60 https://github.com/mcmonkeyprojects/sd-dynamic-thresholding/commit/96238f443ea4df84d211e178562d9264d774a2ae

│ C:\AI\SDNEXT\automatic\modules\call_queue.py:31 in f │ │ 30 │ │ │ try: │ │ ❱ 31 │ │ │ │ res = func(*args, **kwargs) │ │ 32 │ │ │ │ progress.record_results(id_task, res) │

│ C:\AI\SDNEXT\automatic\modules\txt2img.py:69 in txt2img │ │ 68 │ if processed is None: │ │ ❱ 69 │ │ processed = processing.process_images(p) │ │ 70 │ p.close() │

│ C:\AI\SDNEXT\automatic\modules\processing.py:734 in process_images │ │ 733 │ │ │ with context_hypertile_vae(p), context_hypertile_unet(p): │ │ ❱ 734 │ │ │ │ res = process_images_inner(p) │

│ C:\AI\SDNEXT\automatic\extensions-builtin\sd-webui-controlnet\scripts\batch_hij │ │ ack.py:42 in processing_process_images_hijack │ │ 41 │ │ │ # we are not in batch mode, fallback to original function │ │ ❱ 42 │ │ │ return getattr(processing, '__controlnet_original_process_ima │

│ C:\AI\SDNEXT\automatic\modules\processing.py:864 in process_images_inner │ │ 863 │ │ │ │ with devices.without_autocast() if devices.unet_needs_up │ │ ❱ 864 │ │ │ │ │ samples_ddim = p.sample(conditioning=c, unconditiona │ │ 865 │ │ │ │ x_samples_ddim = [decode_first_stage(p.sd_model, samples │

│ C:\AI\SDNEXT\automatic\extensions\sd-webui-bmab-SDNEXT\sd_bmab\sd_override\txt2 │ │ img.py:55 in sample │ │ ❱ 55 │ │ │ self.sampler = sd_samplers.create_sampler(self.sampler_name, │

│ C:\AI\SDNEXT\automatic\extensions\sd-webui-neutral-prompt\lib_neutral_prompt\cf │ │ g_denoiser_hijack.py:254 in create_sampler_hijack │ │ 253 def create_sampler_hijack(name: str, model, original_function): │ │ ❱ 254 │ sampler = original_function(name, model) │ │ 255 │ if not hasattr(sampler, 'model_wrap_cfg') or not hasattr(sampler.mode │

│ C:\AI\SDNEXT\automatic\modules\sd_samplers.py:52 in create_sampler │ │ 51 │ if shared.backend == shared.Backend.ORIGINAL: │ │ ❱ 52 │ │ sampler = config.constructor(model) │ │ 53 │ │ sampler.config = config │

│ C:\AI\SDNEXT\automatic\extensions\sd-webui-samplers-scheduler-for-v1.6\scripts\ │ │ Seniorious.py:231 in │ │ ❱ 231 │ data = [sd_samplers_common.SamplerData(label, lambda model, funcname= │ │ 232 │ │ │ │ │ │ │ │ for label, funcname, aliases, options in │

│ C:\AI\SDNEXT\automatic\extensions\sd-webui-samplers-scheduler-for-v1.6\scripts\ │ │ Seniorious.py:171 in init │ │ 170 │ │ self.extra_params = [] │ │ ❱ 171 │ │ self.model_wrap_cfg = K.CFGDenoiserKDiffusion(self) │ │ 172 │ │ self.model_wrap = self.model_wrap_cfg.inner_model │ ╰─────────────────────────────────────────────────────────────────────────────────╯ AttributeError: module 'modules.sd_samplers_kdiffusion' has no attribute 'CFGDenoiserKDiffusion'

Carzit commented 6 months ago

Thank you for this! I've taken the same solution as the submission you mentioned.