chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update 图片生成.py

Browse Source
This commit is contained in:
binary-husky 2023-11-14 23:15:19 +08:00 committed by GitHub
parent f495bb154e
commit 5caeb7525d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 29 additions and 80 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

109
crazy_functions/图片生成.py
View File

@ -2,7 +2,7 @@ from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log
from crazy_functions.multi_stage.multi_stage_utils import GptAcademicState from crazy_functions.multi_stage.multi_stage_utils import GptAcademicState
def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2"): def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2", quality=None):
import requests, json, time, os import requests, json, time, os
from request_llms.bridge_all import model_info from request_llms.bridge_all import model_info
@ -25,47 +25,7 @@ def gen_image(llm_kwargs, prompt, resolution="1024x1024", model="dall-e-2"):
'model': model, 'model': model,
'response_format': 'url' 'response_format': 'url'
} }
response = requests.post(url, headers=headers, json=data, proxies=proxies) if quality is not None: data.update({'quality': quality})
print(response.content)
try:
image_url = json.loads(response.content.decode('utf8'))['data'][0]['url']
except:
raise RuntimeError(response.content.decode())
# 文件保存到本地
r = requests.get(image_url, proxies=proxies)
file_path = f'{get_log_folder()}/image_gen/'
os.makedirs(file_path, exist_ok=True)
file_name = 'Image' + time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) + '.png'
with open(file_path+file_name, 'wb+') as f: f.write(r.content)
return image_url, file_path+file_name
def gen_image_dalle3(quality, llm_kwargs, prompt, resolution="1024x1024", model="dall-e-3"):
import requests, json, time, os
from request_llms.bridge_all import model_info
proxies = get_conf('proxies')
# Set up OpenAI API key and model
api_key = select_api_key(llm_kwargs['api_key'], llm_kwargs['llm_model'])
chat_endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
# 'https://api.openai.com/v1/chat/completions'
img_endpoint = chat_endpoint.replace('chat/completions','images/generations')
# # Generate the image
url = img_endpoint
headers = {
'Authorization': f"Bearer {api_key}",
'Content-Type': 'application/json'
}
data = {
'prompt': prompt,
'n': 1,
'size': resolution,
'quality': quality,
'model': model,
'response_format': 'url'
}
response = requests.post(url, headers=headers, json=data, proxies=proxies) response = requests.post(url, headers=headers, json=data, proxies=proxies)
print(response.content) print(response.content)
try: try:
@ -126,17 +86,17 @@ def edit_image(llm_kwargs, prompt, image_path, resolution="1024x1024", model="da
@CatchException @CatchException
def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
""" """
txt 输入栏用户输入的文本，例如需要翻译的一段话，再例如一个包含了待处理文件的路径 txt 输入栏用户输入的文本,例如需要翻译的一段话,再例如一个包含了待处理文件的路径
llm_kwargs gpt模型参数，如温度和top_p等，一般原样传递下去就行 llm_kwargs gpt模型参数,如温度和top_p等,一般原样传递下去就行
plugin_kwargs 插件模型的参数，暂时没有用武之地 plugin_kwargs 插件模型的参数,暂时没有用武之地
chatbot 聊天显示框的句柄，用于显示给用户 chatbot 聊天显示框的句柄,用于显示给用户
history 聊天历史，前情提要 history 聊天历史,前情提要
system_prompt 给gpt的静默提醒 system_prompt 给gpt的静默提醒
web_port 当前软件运行的端口号 web_port 当前软件运行的端口号
""" """
history = [] # 清空历史，以免输入溢出 history = [] # 清空历史,以免输入溢出
chatbot.append(("这是什么功能？", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文效果不理想, 请尝试英文Prompt。正在处理中 .....")) chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg") if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
resolution = plugin_kwargs.get("advanced_arg", '1024x1024') resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
image_url, image_path = gen_image(llm_kwargs, prompt, resolution) image_url, image_path = gen_image(llm_kwargs, prompt, resolution)
@ -146,44 +106,32 @@ def 图片生成_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
f'本地文件地址: <br/>`{image_path}`<br/>'+ f'本地文件地址: <br/>`{image_path}`<br/>'+
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>' f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
]) ])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
@CatchException @CatchException
def 图片生成_DALLE3_Standard(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): def 图片生成_DALLE3(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
history = [] # 清空历史，以免输入溢出 history = [] # 清空历史,以免输入溢出
chatbot.append(("这是什么功能？", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文效果不理想, 请尝试英文Prompt。正在处理中 .....")) chatbot.append(("您正在调用“图像生成”插件。", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文Prompt效果不理想, 请尝试英文Prompt。正在处理中 ....."))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 由于请求gpt需要一段时间,我们先及时地做一次界面更新
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg") if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
resolution = plugin_kwargs.get("advanced_arg", '1024x1024') resolution = plugin_kwargs.get("advanced_arg", '1024x1024').lower()
image_url, image_path = gen_image_dalle3("standard", llm_kwargs, prompt, resolution) if resolution.endswith('-hd'):
resolution = resolution.replace('-hd', '')
quality = 'hd'
else:
quality = 'standard'
image_url, image_path = gen_image(llm_kwargs, prompt, resolution, model="dall-e-3", quality=quality)
chatbot.append([prompt, chatbot.append([prompt,
f'图像中转网址: <br/>`{image_url}`<br/>'+ f'图像中转网址: <br/>`{image_url}`<br/>'+
f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>' f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
f'本地文件地址: <br/>`{image_path}`<br/>'+ f'本地文件地址: <br/>`{image_path}`<br/>'+
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>' f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
]) ])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新
@CatchException
def 图片生成_DALLE3_HD(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
history = [] # 清空历史，以免输入溢出
chatbot.append(("这是什么功能？", "[Local Message] 生成图像, 请先把模型切换至gpt-*或者api2d-*。如果中文效果不理想, 请尝试英文Prompt。正在处理中 ....."))
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 由于请求gpt需要一段时间，我们先及时地做一次界面更新
if ("advanced_arg" in plugin_kwargs) and (plugin_kwargs["advanced_arg"] == ""): plugin_kwargs.pop("advanced_arg")
resolution = plugin_kwargs.get("advanced_arg", '1024x1024')
image_url, image_path = gen_image_dalle3("hd", llm_kwargs, prompt, resolution)
chatbot.append([prompt,
f'图像中转网址: <br/>`{image_url}`<br/>'+
f'中转网址预览: <br/><div align="center"><img src="{image_url}"></div>'
f'本地文件地址: <br/>`{image_path}`<br/>'+
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新
class ImageEditState(GptAcademicState): class ImageEditState(GptAcademicState):
# 尚未完成
def get_image_file(self, x): def get_image_file(self, x):
import os, glob import os, glob
if len(x) == 0: return False, None if len(x) == 0: return False, None
@ -204,8 +152,8 @@ class ImageEditState(GptAcademicState):
def reset(self): def reset(self):
self.req = [ self.req = [
{'value':None, 'description': '请先上传图像（必须是.png格式）, 然后再次点击本插件', 'verify_fn': self.get_image_file}, {'value':None, 'description': '请先上传图像（必须是.png格式）, 然后再次点击本插件', 'verify_fn': self.get_image_file},
{'value':None, 'description': '请输入分辨率，可选：256x256, 512x512 或 1024x1024', 'verify_fn': self.get_resolution}, {'value':None, 'description': '请输入分辨率,可选：256x256, 512x512 或 1024x1024', 'verify_fn': self.get_resolution},
{'value':None, 'description': '请输入修改需求，建议您使用英文提示词', 'verify_fn': self.get_prompt}, {'value':None, 'description': '请输入修改需求,建议您使用英文提示词', 'verify_fn': self.get_prompt},
] ]
self.info = "" self.info = ""
@ -230,11 +178,12 @@ class ImageEditState(GptAcademicState):
@CatchException @CatchException
def 图片修改_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port): def 图片修改_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, web_port):
# 尚未完成
history = [] # 清空历史 history = [] # 清空历史
state = ImageEditState.get_state(chatbot, ImageEditState) state = ImageEditState.get_state(chatbot, ImageEditState)
state = state.feed(prompt, chatbot) state = state.feed(prompt, chatbot)
if not state.already_obtained_all_materials(): if not state.already_obtained_all_materials():
chatbot.append(["图片修改（先上传图片，再输入修改需求，最后输入分辨率）", state.next_req()]) chatbot.append(["图片修改（先上传图片,再输入修改需求,最后输入分辨率）", state.next_req()])
yield from update_ui(chatbot=chatbot, history=history) yield from update_ui(chatbot=chatbot, history=history)
return return
@ -251,5 +200,5 @@ def 图片修改_DALLE2(prompt, llm_kwargs, plugin_kwargs, chatbot, history, sys
f'本地文件地址: <br/>`{image_path}`<br/>'+ f'本地文件地址: <br/>`{image_path}`<br/>'+
f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>' f'本地文件预览: <br/><div align="center"><img src="file={image_path}"></div>'
]) ])
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 # 界面更新 yield from update_ui(chatbot=chatbot, history=history) # 刷新界面 界面更新