一.准备工作
首先，开启api保存格式。
其次，保存现有工作流
然后，结果自动下载
看下保存的内容：
3
inputs
seed 563090841476318
steps 40
cfg 8
sampler_name "dpmpp_2m"
scheduler "karras"
denoise 1
model
0 "25"
1 0
positive
0 "13"
1 0
negative
0 "15"
1 0
latent_image
0 "5"
1 0
class_type "KSampler"
_meta
title "KSampler"
5
inputs
width 704
height 960
batch_size 4
class_type "EmptyLatentImage"
_meta
title "Empty Latent Image"
8
inputs
samples
0 "3"
1 0
vae
0 "36"
1 2
class_type "VAEDecode"
_meta
title "VAE Decode"
13
inputs
from_translate "chinese"
to_translate "english"
text "海边 ，只有一个人\n\n"
clip
0 "36"
1 1
class_type "ArgosTranslateCLIPTextEncodeNode"
_meta
title "Argos Translate CLIP Text Encode Node"
14
inputs
text
0 "13"
1 1
PreviewTextNode_0 "By the sea. Naked beauty, full breasts, walking. Only one."
class_type "PreviewTextNode"
_meta
title "Preview Text Node"
15
inputs
text ""
clip
0 "36"
1 1
class_type "CLIPTextEncode"
_meta
title "CLIP Text Encode (Prompt)"
19
inputs
images
0 "8"
1 0
class_type "PreviewImage"
_meta
title "Preview Image"
25
inputs
unet_name "绪儿-写实 帅哥美女模型_东方v4.safetensors"
weight_dtype "fp8_e4m3fn"
class_type "UNETLoader"
_meta
title "Load Diffusion Model"
36
inputs
ckpt_name "213.safetensors"
class_type "CheckpointLoaderSimple"
_meta
title "Load Checkpoint"二.学习例题
安装时提供了三个例子
先学习第一个：代码如下。
第一个：
import json
from urllib import request, parse
import random#This is the ComfyUI api prompt format.#If you want it for a specific workflow you can "enable dev mode options"
#in the settings of the UI (gear beside the "Queue Size: ") this will enable
#a button on the UI to save workflows in api format.#keep in mind ComfyUI is pre alpha software so this format will change a bit.#this is the one for the default workflow
prompt_text = """
{"3": {"class_type": "KSampler","inputs": {"cfg": 8,"denoise": 1,"latent_image": ["5",0],"model": ["4",0],"negative": ["7",0],"positive": ["6",0],"sampler_name": "euler","scheduler": "normal","seed": 8566257,"steps": 20}},"4": {"class_type": "CheckpointLoaderSimple","inputs": {"ckpt_name": "v1-5-pruned-emaonly.safetensors"}},"5": {"class_type": "EmptyLatentImage","inputs": {"batch_size": 1,"height": 512,"width": 512}},"6": {"class_type": "CLIPTextEncode","inputs": {"clip": ["4",1],"text": "masterpiece best quality girl"}},"7": {"class_type": "CLIPTextEncode","inputs": {"clip": ["4",1],"text": "bad hands"}},"8": {"class_type": "VAEDecode","inputs": {"samples": ["3",0],"vae": ["4",2]}},"9": {"class_type": "SaveImage","inputs": {"filename_prefix": "ComfyUI","images": ["8",0]}}
}
"""def queue_prompt(prompt):p = {"prompt": prompt}data = json.dumps(p).encode('utf-8')req = request.Request("http://127.0.0.1:8188/prompt", data=data)request.urlopen(req)prompt = json.loads(prompt_text)
#set the text prompt for our positive CLIPTextEncode
prompt["6"]["inputs"]["text"] = "masterpiece best quality man"#set the seed for our KSampler node
prompt["3"]["inputs"]["seed"] = 5queue_prompt(prompt)替换，我们的工作流的内容。 及必要修改的内容。也可以通过引入的方法。
整体如下：
import json
from urllib import request, parse
import random#This is the ComfyUI api prompt format.#If you want it for a specific workflow you can "enable dev mode options"
#in the settings of the UI (gear beside the "Queue Size: ") this will enable
#a button on the UI to save workflows in api format.#keep in mind ComfyUI is pre alpha software so this format will change a bit.#this is the one for the default workflow
# 这是 ComfyUI API 的提示格式。# 如果你想要特定工作流的格式，可以在 UI 设置中启用“开发模式选项”
# （队列大小旁边的齿轮图标），这将启用一个按钮，允许你保存工作流为 API 格式。# 请注意，ComfyUI 是预 alpha 软件，所以这个格式可能会有一些变化。prompt_text = """
{{"3": {"inputs": {"seed": 563090841476318,"steps": 40,"cfg": 8,"sampler_name": "dpmpp_2m","scheduler": "karras","denoise": 1,"model": ["25",0],"positive": ["13",0],"negative": ["15",0],"latent_image": ["5",0]},"class_type": "KSampler","_meta": {"title": "KSampler"}},"5": {"inputs": {"width": 704,"height": 960,"batch_size": 4},"class_type": "EmptyLatentImage","_meta": {"title": "Empty Latent Image"}},"8": {"inputs": {"samples": ["3",0],"vae": ["36",2]},"class_type": "VAEDecode","_meta": {"title": "VAE Decode"}},"13": {"inputs": {"from_translate": "chinese","to_translate": "english","text": "这里是本次要替换的内容","clip": ["36",1]},"class_type": "ArgosTranslateCLIPTextEncodeNode","_meta": {"title": "Argos Translate CLIP Text Encode Node"}},"14": {"inputs": {"text": ["13",1],"PreviewTextNode_0": "By the sea. Naked beauty, full breasts, walking. Only one."},"class_type": "PreviewTextNode","_meta": {"title": "Preview Text Node"}},"15": {"inputs": {"text": "","clip": ["36",1]},"class_type": "CLIPTextEncode","_meta": {"title": "CLIP Text Encode (Prompt)"}},"19": {"inputs": {"images": ["8",0]},"class_type": "PreviewImage","_meta": {"title": "Preview Image"}},"25": {"inputs": {"unet_name": "绪儿-写实 帅哥美女模型_东方v4.safetensors","weight_dtype": "fp8_e4m3fn"},"class_type": "UNETLoader","_meta": {"title": "Load Diffusion Model"}},"36": {"inputs": {"ckpt_name": "213.safetensors"},"class_type": "CheckpointLoaderSimple","_meta": {"title": "Load Checkpoint"}}
}
"""def queue_prompt(prompt):p = {"prompt": prompt}data = json.dumps(p).encode('utf-8')req = request.Request("http://127.0.0.1:8188/prompt", data=data)request.urlopen(req)prompt = json.loads(prompt_text)
#set the text prompt for our positive CLIPTextEncode
prompt["13"]["inputs"]["text"] = "这里是你要替换的内容"# #set the seed for our KSampler node
# prompt["3"]["inputs"]["seed"] = 5queue_prompt(prompt)运行出错：
python script_examples/basic_api_learn.py
Traceback (most recent call last):
File "/home/duyicheng/gitee/ComfyUI/script_examples/basic_api_learn.py", line 163, in <module>
prompt = json.loads(prompt_text)
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/duyicheng/anaconda3/envs/comfyui/lib/python3.12/json/__init__.py", line 346, in loads
return _default_decoder.decode(s)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/duyicheng/anaconda3/envs/comfyui/lib/python3.12/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/duyicheng/anaconda3/envs/comfyui/lib/python3.12/json/decoder.py", line 353, in raw_decode
obj, end = self.scan_once(s, idx)
^^^^^^^^^^^^^^^^^^^^^^
json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 3 column 5 (char 7)
原来是多了两个花括号，这提醒我们，在复制时一定要稳定。
再次运行3次
队列也能看到。
但卡得不动，不知是什么原因。就当是成功了吧。
学习第二个
很简单，结合第一个，一次成功。注意安装第一个模块时，不要太高。否则不行。
第三个就不学了。