【高端操作】一张图扩增全角度表情光影素材

滚石

星级打分

• 1
• 2
• 3
• 4
• 5

平均分:5  参与人数:5  我的评分:未评

视频教程来啦



相关资源下载链接（工作流，instantid相关模型，基础模型）
夸克盘链接：https://pan.quark.cn/s/9864d8adbb7e

百度盘链接：https://pan.baidu.com/s/1WwSNkMo3ecUPXTfvleC1hQ?pwd=7n7g
所有模型一股脑放到comfyui的model目录下即可

云主机镜像在dflyun.com，选下图这个镜像


--------------------------------------之前预告内容------------------------------------------------------------------------------------------------------------------
comfyui真是个好东西，自己搭建自定义工作流，结合相关算法和提示词，实现只输入一张人脸图，即可保持人物身份不变，得到更多表情光影角度。 参考效果如下图



效果是真强大，但comfyui上限高门槛也高，对新人及其不友好，不像webui随便点点都能出图。comfyui起码是得理解AI绘画底层原理才能上手
整套工作流背后的模型都有大概60G了。尤其那个instantid算法，坑是真的多，过年期间就开始搞，搞到现在才顺利跑通。
这东西又没法做成简单一键式傻瓜包，不同素材需要调试不同模型和提示词，不同底模对应的采样器CFG都不一样，全部打包好也不见得其他电脑直接能跑，出教程还得等一段时间
用到的相关算法模型有SDXL, SDXL turbo，LCM， ipadapter，controlnet，instantid，SAM，CLIP，以及一大堆comfyui社区插件

如果你有素材扩增、人脸混血、无版权合成人素材制造、高级图片换脸等需求，可以联系我老婆QQ845289815 人工处理

snig

antony0702 发表于 2024-4-5 21:05
有人知道为啥人物都只会笑吗
换了好多模型还是一样

上C站，以realistic为关键字搜模型，找标注为checkpoint|XL的模型。
可以先试试Realistic Stock Photo和RealVisXL V4.0。
XL模型都比较大，这两是6.46G。
下载放到model/checkpoint/目录，启动以后选取即可。

猪悟能

When loading the graph, the following node types were not found:
ApplyInstantIDAdvanced
InstantIDFaceAnalysis
InstantIDModelLoader
加载失败的节点会显示为红色

为什么这三个会红···救救孩子

orgasmpan

ktis321 发表于 2024-3-29 14:35
Error occurred when executing PreviewImage:

'NoneType' object is not subscriptable

将最下面的 <WAS Node Suite> 和 <预览图像> 右键 <忽略节点>。

糖伯斧

Error occurred when executing KSampler:

'NoneType' object has no attribute 'shape'

File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\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 "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\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 "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\nodes.py", line 1344, in sample
return common_ksampler(model, seed, steps, cfg, sampler_name, scheduler, positive, negative, latent_image, denoise=denoise)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\nodes.py", line 1314, in common_ksampler
samples = comfy.sample.sample(model, noise, steps, cfg, sampler_name, scheduler, positive, negative, latent_image,
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\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 "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-AnimateDiff-Evolved\animatediff\sampling.py", line 279, in motion_sample
return orig_comfy_sample(model, noise, *args, **kwargs)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Advanced-ControlNet\adv_control\control_reference.py", line 47, in refcn_sample
return orig_comfy_sample(model, *args, **kwargs)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\sample.py", line 37, 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 "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 755, 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 "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 657, in sample
return cfg_guider.sample(noise, latent_image, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 644, in sample
output = self.inner_sample(noise, latent_image, device, sampler, sigmas, denoise_mask, callback, disable_pbar, seed)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 623, in inner_sample
samples = sampler.sample(self, sigmas, extra_args, callback, noise, latent_image, denoise_mask, disable_pbar)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 534, in sample
samples = self.sampler_function(model_k, noise, sigmas, extra_args=extra_args, callback=k_callback, disable=disable_pbar, **self.extra_options)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\python\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\k_diffusion\sampling.py", line 154, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 272, in __call__
out = self.inner_model(x, sigma, model_options=model_options, seed=seed)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 610, in __call__
return self.predict_noise(*args, **kwargs)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 613, 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 "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 258, in sampling_function
out = calc_cond_batch(model, conds, x, timestep, model_options)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\samplers.py", line 192, in calc_cond_batch
c['control'] = control.get_control(input_x, timestep_, c, len(cond_or_uncond))
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\controlnet.py", line 184, 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)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\python\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "C:\DD\2-xiazai\ComfyUI-aki(2)\ComfyUI-aki-v1.3\ComfyUI-aki-v1.3\comfy\cldm\cldm.py", line 295, in forward
assert y.shape[0] == x.shape[0]


铁子们，这是啥子问题哇

天光脑震荡

小幸运 发表于 2024-5-1 09:44
大哥，链接过期了，还能再分享一遍吗

链接：https://pan.baidu.com/s/1r6Qp0AMuscnvSBcIoXAbIg
提取码：5693
--来自百度网盘超级会员V8的分享

天光脑震荡

kdq751 发表于 2024-3-30 14:13
是comfyui版本太低吗？如何升级到最新啊

告诉你一个一步到位的方法：花点钱租滚石的云主机，把里面的ComfyUI整个文件一共50多G复制出来或者传到网盘上在自己的机子上下载下来就可以了

jy19931123

zzwei200 发表于 2024-3-27 17:21
请教一下，我在家里（4090）出图是正常的，但在公司（4060ti 16G)用这个工作流就没出过人，都是一堆乱码或 ...

内核版本点全部升级，然后把comfy/ldm/modules/diffusionmodules/openaimodel.py这个文件替换掉，下面是用来替换的文件下载链接

1. https://github.com/comfyanonymous/ComfyUI/blob/b3e97fc7141681b1fa6da3ee6701c0f9a31d38f8/comfy/ldm/modules/diffusionmodules/openaimodel.py

复制代码

Deannnn

这个就是你前阵子群里发的那个？

天光脑震荡

我要我要我要！！！

bbking2018

期待滚总早日出教程扫除我们这些文盲。

seancai110

comfyui是很厉害，但是那密密麻麻的节点看着头痛。

htyy

是啊门槛高，也很难做成傻瓜式打包

燕翎风

期待早日出教程教教我们这些小白

pasanonic

为什么联系你老婆

滚石

pasanonic 发表于 2024-3-10 19:23
为什么联系你老婆

因为我要上班干活

liu7788345

期待教程