Incompatibility with stable-diffusion-webui-reForge

[zslittlehelper]

Reforge is both faster and feels more polished than regular A1111. I tried CharacteristicGuidance with the dev_upstream branch and there's an immediate incompatibility regardless of any settings.

I did not test whether it works with the Main branch.

Characteristic Guidance parameters registered Characteristic Guidance enabled, warpping the sample method Characteristic Guidance modifying the CFGDenoiser *********cfg denoiser res thres def ************ Characteristic Guidance sampling: 0%| | 0/32 [00:00<?, ?it/s] Characteristic Guidance recorded iterations info for 0 steps Characteristic Guidance recovering the CFGDenoiser Traceback (most recent call last): File "C:\SDV_18\stable-diffusion-webui-reForge\modules_forge\main_thread.py", line 37, in loop task.work() File "C:\SDV_18\stable-diffusion-webui-reForge\modules_forge\main_thread.py", line 26, in work self.result = self.func(*self.args, **self.kwargs) File "C:\SDV_18\stable-diffusion-webui-reForge\modules\txt2img.py", line 110, in txt2img_function processed = processing.process_images(p) File "C:\SDV_18\stable-diffusion-webui-reForge\modules\processing.py", line 823, in process_images res = process_images_inner(p) File "C:\SDV_18\stable-diffusion-webui-reForge\modules\processing.py", line 970, 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 "C:\SDV_18\stable-diffusion-webui-reForge\extensions\CharacteristicGuidanceWebUI\scripts\CHGextension.py", line 441, in wrapper raise e File "C:\SDV_18\stable-diffusion-webui-reForge\extensions\CharacteristicGuidanceWebUI\scripts\CHGextension.py", line 437, in wrapper result = sample(conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength, File "C:\SDV_18\stable-diffusion-webui-reForge\modules\processing.py", line 1340, in sample samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x)) File "C:\SDV_18\stable-diffusion-webui-reForge\modules\sd_samplers_kdiffusion.py", line 263, in sample samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs)) File "C:\SDV_18\stable-diffusion-webui-reForge\modules\sd_samplers_common.py", line 274, in launch_sampling return func() File "C:\SDV_18\stable-diffusion-webui-reForge\modules\sd_samplers_kdiffusion.py", line 263, in <lambda> samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args=self.sampler_extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs)) File "C:\SDV_18\stable-diffusion-webui-reForge\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "C:\SDV_18\stable-diffusion-webui-reForge\modules\sd_samplers_kdiffusion_smea.py", line 92, in sample_euler_dy denoised = model(x, sigma_hat * s_in, **extra_args) File "C:\SDV_18\stable-diffusion-webui-reForge\venv\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "C:\SDV_18\stable-diffusion-webui-reForge\venv\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl return forward_call(*args, **kwargs) File "C:\SDV_18\stable-diffusion-webui-reForge\extensions\CharacteristicGuidanceWebUI\scripts\CHGextension.py", line 400, in _call_forward return CHGDenoiser.forward(self, *args, **kwargs) File "<string>", line 36, in forward File "C:\SDV_18\stable-diffusion-webui-reForge\extensions\CharacteristicGuidanceWebUI\scripts\forge_CHG.py", line 266, in forge_sample denoised = sampling_function(self,model, x, timestep, uncond, cond, cond_scale, model_options, seed) File "C:\SDV_18\stable-diffusion-webui-reForge\extensions\CharacteristicGuidanceWebUI\scripts\forge_CHG.py", line 196, in sampling_function cond_pred, uncond_pred = calc_cond_uncond_batch(self,model, cond, uncond_, x, timestep, model_options,cond_scale) File "C:\SDV_18\stable-diffusion-webui-reForge\extensions\CharacteristicGuidanceWebUI\scripts\forge_CHG.py", line 132, in calc_cond_uncond_batch transformer_options["cond_mark"] = compute_cond_mark(cond_or_uncond=cond_or_uncond, sigmas=timestep) NameError: name 'compute_cond_mark' is not defined name 'compute_cond_mark' is not defined *** Error completing request *** Arguments: ('task(r7y3phb7tq6na9g)', <gradio.routes.Request object at 0x000002785A426FB0>, 'cute dog', 'angry dog', [], 1, 1, 3.5, 1024, 1128, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', 'Use same scheduler', '', '', [], 0, 32, 'Euler Dy', 'Align Your Steps', False, '', 0.8, -1, False, -1, 0, 0, 0, 1, 0, 0.01, 50, 0, 1, -4, 1, 0.4, 0.5, 2, True, '[How to set parameters? Check our github!](https://github.com/scraed/CharacteristicGuidanceWebUI/tree/main)', 'More ControlNet', 0, 1, 0.4, ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], multi_inputs_gallery=[], generated_image=None, mask_image=None, hr_option=<HiResFixOption.BOTH: 'Both'>, enabled=False, module='None', model='None', weight=1, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, advanced_weighting=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], multi_inputs_gallery=[], generated_image=None, mask_image=None, hr_option=<HiResFixOption.BOTH: 'Both'>, enabled=False, module='None', model='None', weight=1, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, advanced_weighting=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, save_detected_map=True), ControlNetUnit(input_mode=<InputMode.SIMPLE: 'simple'>, use_preview_as_input=False, batch_image_dir='', batch_mask_dir='', batch_input_gallery=[], batch_mask_gallery=[], multi_inputs_gallery=[], generated_image=None, mask_image=None, hr_option=<HiResFixOption.BOTH: 'Both'>, enabled=False, module='None', model='None', weight=1, image=None, resize_mode=<ResizeMode.INNER_FIT: 'Crop and Resize'>, processor_res=-1, threshold_a=-1, threshold_b=-1, guidance_start=0, guidance_end=1, pixel_perfect=False, control_mode=<ControlMode.BALANCED: 'Balanced'>, advanced_weighting=None, pulid_mode=<PuLIDMode.FIDELITY: 'Fidelity'>, union_control_type=<ControlNetUnionControlType.UNKNOWN: 'Unknown'>, save_detected_map=True), False, 7, 1, 'Constant', 0, 'Constant', 0, 1, 'enable', 'MEAN', 'AD', 1, False, 1.01, 1.02, 0.99, 0.95, False, 0.5, 2, False, 256, 2, 0, False, False, False, True, True, False, True, 1, False, 5.5, 1, 1, False, 'Quack expert', True, 0, 'From preset', False, True, 1000, 7.5, True, 'hard', 8, 1000, 5, False, 'Single Scale', 7, False, False, 7, 5, 5, False, 3, 2, 0, 0.35, True, 'bicubic', 'bicubic', False, 9, -0.05, 15, 1, False, 0.7, False, 'Discrete', 'eps', True, 'v_prediction', 120, 0.002, 120, 0.002, 2, 2, 2, 1.15, 0.5, 1024, 1024, False, False, 'SD15', 'high (1536-2048)', 'default', 'default', False, 'SD15', '3', '8', 'percent', 0, 0.45, False, 'bicubic', 0, 0.3, '4', '8', 'bicubic', False, 'SD15', False, 'SD15', '3', '', '8', 'percent', 0, 0.45, False, 0, 'anisotropic', 0, 'reinhard', 100, 0, 'subtract', 0, 0, 'gaussian', 'add', 0, 100, 127, 0, 'hard_clamp', 5, 0, 'None', 'None', False, 'Average', 0.5, 0.5, 1, 10, False, 20, False, 20, 20, 'SD1', False, '((1 - cos(2 * pi * (1-y**0.5) * 0.5)) / 2)*sigmax+((1 - cos(2 * pi * y**0.5 * 0.5)) / 2)*sigmin', 20, False, False, 'MultiDiffusion', 768, 768, 64, 4, False, False, '', '', '', 'none', 'comfy', 'disable', 0.5, False, False, False, 'Disabled', 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 "C:\SDV_18\stable-diffusion-webui-reForge\modules\call_queue.py", line 74, in f res = list(func(*args, **kwargs)) TypeError: 'NoneType' object is not iterable

[scraed]

Hi, I’m not very familiar with ReForge code, but will try to look at it.

[zslittlehelper]

dev_upstream no longer exists since a while back. Re-tested with the main branch and CharacteristicGuidance has the same issue.
(Just added this as additional information.)