nodes/MinusZoneAI-ComfyUI-Prompt-MZ

Fork 0

T

wailovet a5b14815f3 'update'

2024-04-30 14:26:48 +08:00

res

'update'

2024-04-23 02:52:38 +08:00

__init__.py

'update'

2024-04-30 12:41:16 +08:00

.gitignore

init

2024-04-23 00:29:56 +08:00

LICENSE

init

2024-04-23 00:29:56 +08:00

mz_gen_translate.py

'update'

2024-04-30 14:26:48 +08:00

mz_llama3.py

'update'

2024-04-27 23:39:41 +08:00

mz_llama_cpp.py

'update'

2024-04-30 12:46:04 +08:00

mz_llava.py

'update'

2024-04-30 12:41:16 +08:00

mz_phi3.py

'update'

2024-04-28 16:33:42 +08:00

mz_prompt_utils.py

'update'

2024-04-30 12:46:04 +08:00

mz_prompts.py

'update'

2024-04-27 23:39:41 +08:00

mz_qwen.py

'update'

2024-04-24 02:39:14 +08:00

README.md

'update'

2024-04-30 12:46:04 +08:00

README.md

ComfyUI-Prompt-MZ

基于llama.cpp的一些和提示词相关的节点，目前包括美化提示词和类似clip-interrogator的图片反推

Use llama.cpp to assist in generating some nodes related to prompt words, including beautifying prompt words and image recognition similar to clip-interrogator

Recent changes

[2024-04-30] 添加llava-v1.6-vicuna-13b (add llava-v1.6-vicuna-13b)
[2024-04-30] 添加翻译
[2024-04-28] 新增Phi-3-mini节点 (add Phi-3-mini node)

Installation

Clone this repo into custom_nodes folder.
Restart ComfyUI.

Nodes

CLIPTextEncode (Phi-3)
CLIPTextEncode (LLama3)
ImageInterrogator (LLava)

Enable parameter sd_format
LLamaCPPOptions
BaseLLamaCPPCLIPTextEncode (可以手动传入模型路径/You can directly pass in the model path)
BaseLLavaImageInterrogator (可以手动传入模型路径/You can directly pass in the model path)