smthemex / ComfyUI_StoryDiffusion

You can using StoryDiffusion in ComfyUI
Apache License 2.0
241 stars 195 forks source link

两个人一起出现在一个画面怎么写 #13

Closed xueqing0622 closed 2 months ago

xueqing0622 commented 5 months ago

[Bob] [Alice] on the road, near the forest; 我这样写,提示 Error occurred when executing Storydiffusion_Text2Img:

exceptions must derive from BaseException

File "F:\ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\Storydiffusion_node.py", line 1055, in text2image for value in gen: File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\Storydiffusion_node.py", line 718, in process_generation ) = process_original_prompt(character_dict, prompts.copy(), id_length) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\utils\gradio_utils.py", line 508, in process_original_prompt raise f"{character_key} not have enough prompt description, need no less than {id_length}, but you give {len(index_list)}"

Close

xueqing0622 commented 5 months ago

我看官方文档有两个角色一起的画面 不知道这个插件里面如何实现 image

xueqing0622 commented 5 months ago

找到原因了,上面书写没有问题,好像txt2img必须是7句话,不然就会上面的错误。 而且不过两个角色在一起,好像会污染。角色统一性就不好了

smthemex commented 5 months ago

是角色的数量要一致,也就是你2个角色,下面有个角色数量那里必须是2,然后场景的里面,必须出现这两个角色的名字一次

xueqing0622 commented 5 months ago

好像低于7句话也可以,我也不知道为什么

smthemex commented 5 months ago

跟句子长度没什么关系,要角色数量对得上。双角色出现在一个画面等后面更新

xueqing0622 commented 5 months ago

谢谢解答 期待双角色在同一画面更新 image

xueqing0622 commented 5 months ago

这样也u错,是什么原因。 image

!! Exception during processing!!! exceptions must derive from BaseException Traceback (most recent call last): File "F:\ComfyUI\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\execution.py", line 81, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\Storydiffusion_node.py", line 1055, in text2image for value in gen: File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\Storydiffusion_node.py", line 718, in process_generation ) = process_original_prompt(character_dict, prompts.copy(), id_length) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "F:\ComfyUI\ComfyUI\custom_nodes\ComfyUI_StoryDiffusion\utils\gradio_utils.py", line 508, in process_original_prompt raise f"{character_key} not have enough prompt description, need no less than {id_length}, but you give {len(index_list)}" TypeError: exceptions must derive from BaseException

smthemex commented 5 months ago

角色关键词是img,在角色栏要有这个photomaker才生效,我去主页备注一下

xueqing0622 commented 5 months ago

感谢,期待双角色一起出现画面

piovis2023 commented 4 months ago

Is there a fix for this problem yet? Thank you

smthemex commented 4 months ago

If using dual characters, each character needs to appear at least twice in the scene prompt words to avoid errors. This is not a bug, I have tried to fix it, but it will bring unexpected errors. 使用双角色时,需要每个角色在场景提示词中,出现2次以上(不包含双人同框)