wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-02-04 10:40:30 +08:00
Code Issues Actions 18 Packages Projects Releases Wiki Activity

Return typo 'prompt'

Browse Source
This commit is contained in:
Mihail Karaev 2026-02-02 09:04:35 +00:00
parent 6c70d12f07
commit c55a6fb271
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
comfy/text_encoders/kandinsky5.py
View File

@ -6,7 +6,7 @@ from .llama import Qwen25_7BVLI
class Kandinsky5Tokenizer(QwenImageTokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data)
self.llama_template = "<|im_start|>system\nYou are a prompt engineer. Describe the video in detail.\nDescribe how the camera moves or shakes, describe the zoom and view angle, whether it follows the objects.\nDescribe the location of the video, main characters or objects and their action.\nDescribe the dynamism of the video and presented actions.\nName the visual style of the video: whether it is a professional footage, user generated content, some kind of animation, video game or screen content.\nDescribe the visual effects, postprocessing and transitions if they are presented in the video.\nPay attention to the order of key actions shown in the scene.<|im_end|>\n<|im_start|>user\n{}<|im_end|>"
self.llama_template = "<|im_start|>system\nYou are a promt engineer. Describe the video in detail.\nDescribe how the camera moves or shakes, describe the zoom and view angle, whether it follows the objects.\nDescribe the location of the video, main characters or objects and their action.\nDescribe the dynamism of the video and presented actions.\nName the visual style of the video: whether it is a professional footage, user generated content, some kind of animation, video game or screen content.\nDescribe the visual effects, postprocessing and transitions if they are presented in the video.\nPay attention to the order of key actions shown in the scene.<|im_end|>\n<|im_start|>user\n{}<|im_end|>"
self.clip_l = sd1_clip.SDTokenizer(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data)
def tokenize_with_weights(self, text:str, return_word_ids=False, **kwargs):