ComfyUI Extension: ComfyUI_zfkun
A collection of nodes for common tools, including text preview, text translation (multi-platform, multi-language), image loader, webcamera capture.
Custom Nodes (5)
README
ComfyUI zfkun
Custom nodes pack for ComfyUI
ChangeLog
2025-03-24
- update version to
0.0.12
- add bigmodel platform for text translate node
- add siliconflow platform for text translate node
2025-03-10
-
update version to
0.0.11
-
Fix the script failure problem caused by changes in the logic related to
WEB_DIRECTORY
. -
update version to
0.0.10
-
fix detection logic for requirement package. See #6
-
fix preview video position for
Share Screen
node
2025-01-01
- update version to
0.0.9
- fix language code of
Simplified Chinese
forText Translation
node Comfy Registry
support
2024-01-21
- update version to
0.0.8
- add error tips for
Share Screen
node - Optimize some logic for
Share Screen
node
2024-01-06
- update version to
0.0.7
- add
Clip Area
support forShare Screen
node - add
Refresh Duration
support forShare Screen
node
2023-12-27
- add
Window Capture Simple
Server (WIP)
2023-12-24
- update version to
0.0.6
- add
Share Screen
node
2023-12-17
- update version to
0.0.5
- fix translation error for
alibaba
platform - fix translator name typo for
tencent
platform
2023-12-17
- update version to
0.0.4
- update README
- add
Load Image Path
node - add
Camera Capture Simple
server
2023-12-16
-
update version to
0.0.3
-
add niutrans platform for text translate node
2023-12-15
-
update version to
0.0.2
-
add auto converting encoding to
utf-8
forconfig.yaml
-
add auto install requirements
2023-12-08
-
add baidu, alibaba, tencent, volcengine platform for text translate node
-
update README
Installation
Using ComfyUI Manager (recommended)
Install ComfyUI Manager and do steps introduced there to install this repo.
Alternative
cd ComfyUI/custom_nodes/
git clone https://github.com/zfkun/ComfyUI_zfkun
# comfyui use system python
pip install -r requirements.txt
# if comfyui use venv
# path/to/ComfUI/venv/bin/python -s -m pip install -r requirements.txt
# restart ComfyUI
Server
Camera Capture Simple
a simple camera capture server.
mainly used with Load Image Path
and LCM
for real-time virtual live workflow
feature
- custom capture source (0, 1, 2 ...)
- custom output directory
- custom output filename (
*
will be replaced by%Y%m%d_%H%M%S
)
useage
the paths to
ComfyUI
andpython
need to be modified to suit for you.
in my case,
ComfyUI
in./ComfyUI
andpython
in./ComfyUI/venv
with venv
basic
# enter ComfyUI's home
cd ./ComfyUI
# active virtual environment for python
source ./venv/bin/activate
# enter server's home
cd ./custom_nodes/ComfyUI_zfkun/server
# start server with custom output directory
python camera_capture_simple.py -o ~/ai/sd/output_webcam
<img src="./usage_camera_capture_simple_server_1.png" width="600" />
advanced
python camera_capture_simple.py -h
<img src="./usage_camera_capture_simple_server_2.png" width="600" />
Nodes
Preview Text
support textใprimitive (text) for input
Preview Text (Multiline)
support textใprimitive (clip text) for input
Text Translation
support platforms:
- baidu (็พๅบฆ็ฟป่ฏ)
- alibaba (้ฟ้็ฟป่ฏ)
- tencent (่ พ่ฎฏ็ฟป่ฏ)
- volcengine (็ซๅฑฑ็ฟป่ฏ)
- niutrans (ๅฐ็็ฟป่ฏ)
- bigmodel (ๆบ่ฐฑ GLM)
default model:
glm-4-flash
(free)support model:
glm-4-plus
ใglm-4-air
ใglm-4-air-0111
(Preview)ใglm-4-airx
ใglm-4-long
ใglm-4-flashx
ใglm-4-flash
(free) - siliconflow (็ก
ๅบๆตๅจ)
default model:
Qwen/Qwen2.5-7B-Instruct
(free)support model:
Qwen/QwQ-32B
,Pro/deepseek-ai/DeepSeek-R1
,Pro/deepseek-ai/DeepSeek-V3
,deepseek-ai/DeepSeek-R1
,deepseek-ai/DeepSeek-V3
,deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
,deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
,deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
(free),deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
(free),Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
,Pro/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
,deepseek-ai/DeepSeek-V2.5
,Qwen/Qwen2.5-72B-Instruct-128K
,Qwen/Qwen2.5-72B-Instruct
,Qwen/Qwen2.5-32B-Instruct
,Qwen/Qwen2.5-14B-Instruct
,Qwen/Qwen2.5-7B-Instruct
(free),Qwen/Qwen2.5-Coder-32B-Instruct
,Qwen/Qwen2.5-Coder-7B-Instruct
(free),Qwen/Qwen2-7B-Instruct
(free),Qwen/Qwen2-1.5B-Instruct
(free),Qwen/QwQ-32B-Preview
,TeleAI/TeleChat2
,THUDM/glm-4-9b-chat
(free),Vendor-A/Qwen/Qwen2.5-72B-Instruct
,internlm/internlm2_5-7b-chat
(free),internlm/internlm2_5-20b-chat
,Pro/Qwen/Qwen2.5-7B-Instruct
,Pro/Qwen/Qwen2-7B-Instruct
,Pro/Qwen/Qwen2-1.5B-Instruct
,Pro/THUDM/chatglm3-6b
,Pro/THUDM/glm-4-9b-chat
- create
config.yaml
(copy fromconfig.yaml.example
, make sure file encoding isutf-8
)- update
translator
field, save- restart
ComfyUI
Load Image Path
- support
path
(relativeใabsoluteใ~ใ~user)) - support
url
(httpใhttps) - support
RGBA
for output image - support
default image
for input
Share Screen
- support windowใtabใscreen share
- support multiple share node at the same time
- support custom clip area
- support custom refresh duration
- support default image (
RGBA
support) - support weight and prompt