Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

TextEncodeV2 and UNETLoaderV2 cannot create photos (只出黑图),as well as the ControlNet. #47

Open
banyeshuiwujiao opened this issue Jul 21, 2024 · 5 comments

Comments

@banyeshuiwujiao
Copy link

新版的TextEncodeV2和UNETLoaderV2无法出图,ControlNet也不能用, 以下图片是我的测试工作流
kolors-text2image-noCreatePhoto

换成旧版的可以,但是旧版的没法用ControlNet,报错:'UNetModel' object has no attribute 'encoder_hid_proj'
old TextEncode for ControlNet workflow is Error

Error occurred when executing KSampler:

'UNetModel' object has no attribute 'encoder_hid_proj'

File "D:\Program Files\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "D:\Program Files\ComfyUI-aki-v1.3\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "D:\Program Files\ComfyUI-aki-v1.3\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "D:\Program Files\ComfyUI-aki-v1.3\nodes.py", line 1373, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "D:\Program Files\ComfyUI-aki-v1.3\nodes.py", line 1343, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "D:\Program Files\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Impact-Pack\modules\impact\sample_error_enhancer.py", line 9, in informative_sample
return original_sample(*args, **kwargs) # This code helps interpret error messages that occur within exceptions but does not have any impact on other operations.
File "D:\Program Files\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 248, in motion_sample
return orig_comfy_sample(model, noise, *args, **kwargs)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\sample.py", line 43, in sample
samples = sampler.sample(noise, positive, negative, cfg=cfg, latent_image=latent_image, start_step=start_step, last_step=last_step, force_full_denoise=force_full_denoise, denoise_mask=noise_mask, sigmas=sigmas, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 817, in sample
return sample(self.model, noise, positive, negative, cfg, self.device, sampler, sigmas, self.model_options, latent_image=latent_image, denoise_mask=denoise_mask, callback=callback, disable_pbar=disable_pbar, seed=seed)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 717, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 704, in sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 683, in inner_sample
samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 588, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "D:\Program Files\ComfyUI-aki-v1.3\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\k_diffusion\sampling.py", line 732, in sample_dpmpp_2m_sde_gpu
return sample_dpmpp_2m_sde(model, x, sigmas, extra_args=extra_args, callback=callback, disable=disable, eta=eta, s_noise=s_noise, noise_sampler=noise_sampler, solver_type=solver_type)
File "D:\Program Files\ComfyUI-aki-v1.3\python\lib\site-packages\torch\utils_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\k_diffusion\sampling.py", line 635, in sample_dpmpp_2m_sde
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 299, in call
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 670, in call
return self.predict_noise(*args, **kwargs)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 673, in predict_noise
return sampling_function(self.inner_model, x, timestep, self.conds.get("negative", None), self.conds.get("positive", None), self.cfg, model_options=model_options, seed=seed)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 279, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\samplers.py", line 202, in calc_cond_batch
c['control'] = control.get_control(input_x, timestep_, c, len(cond_or_uncond))
File "D:\Program Files\ComfyUI-aki-v1.3\comfy\controlnet.py", line 200, in get_control
control = self.control_model(x=x_noisy.to(dtype), hint=self.cond_hint, timesteps=timestep.float(), context=context.to(dtype), y=y, **self.extra_args)
File "D:\Program Files\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "D:\Program Files\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "D:\Program Files\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Kolors-MZ\mz_kolors_core.py", line 222, in KolorsControlNet_forward
context = model.model.diffusion_model.encoder_hid_proj(context)
File "D:\Program Files\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1709, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")

@banyeshuiwujiao
Copy link
Author

@banyeshuiwujiao banyeshuiwujiao changed the title 新版的TextEncodeV2和UNETLoaderV2无法出图,ControlNet也不能用 TextEncodeV2 and UNETLoaderV2 cannot create photos,as well as the ControlNet. Jul 21, 2024
@banyeshuiwujiao banyeshuiwujiao changed the title TextEncodeV2 and UNETLoaderV2 cannot create photos,as well as the ControlNet. TextEncodeV2 and UNETLoaderV2 cannot create photos (只出黑图),as well as the ControlNet. Jul 21, 2024
@wailovet
Copy link
Contributor

Diagnostics-1721556795.log

用的秋叶吗,有没有开了什么优化项,精度尝试一下设置在fp32看看

@banyeshuiwujiao
Copy link
Author

solved,已解决,回来报告一下:
Empty latent Image必须用默认的7681024,才可以用新版V2出图,512512就是黑图,不知道原因

@banyeshuiwujiao
Copy link
Author

更新到torch1.24+cu121,

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants
@wailovet @banyeshuiwujiao and others