hallatore / stable-diffusion-webui-chatgpt-utilities Goto Github PK

Currently the only option to set the key is to store it as a plain text in config.json
Would be super useful to add something like this:

openai.api_key = shared.opts.data.get("chatgpt_utilities_api_key", "")
if openai.api_key == "":
openai.api_key = os.getenv("ENVNAME" default="")
if openai.api_key == "":
raise Exception("OpenAI API Key is not set. Please set it in the settings menu.")

Hi，
Thanks for ur great work, when I use this extension ,i meet the following question:
I cloned this project to the webui/extensions and I can see this extension in installed column，but I cannot find it in Function bar

hello
good extensions, i'm glad to use this
but i can use it just only one time after i install this

and always after restart the colab, this happens

Error loading script: chatgpt_utils.py
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/chatgpt_utils.py", line 3, in
import openai
ModuleNotFoundError: No module named 'openai'

Error loading script: json_utils.py
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/json_utils.py", line 2, in
import json5
ModuleNotFoundError: No module named 'json5'

Error loading script: prompt_chatgpt.py
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/prompt_chatgpt.py", line 3, in
import openai
ModuleNotFoundError: No module named 'openai'

what is the problem? im not major in computer and i dont know python so i cannot handle it.. please help

After you answer with my question,

Error loading script: chatgpt_utils.py
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/chatgpt_utils.py", line 3, in
import openai
ModuleNotFoundError: No module named 'openai'

Error loading script: json_utils.py
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/json_utils.py", line 2, in
import json5
ModuleNotFoundError: No module named 'json5'

Error loading script: prompt_chatgpt.py
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 229, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "", line 850, in exec_module
File "", line 228, in _call_with_frames_removed
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/prompt_chatgpt.py", line 3, in
import openai
ModuleNotFoundError: No module named 'openai'

this error happened again after 1day i restart the colab
so i install json5 and openai by using the code

pip uninstall openai
pip install --upgrade pip
pip install openai
pip install json5

but the error

Error loading script: prompt_chatgpt.py
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/scripts.py", line 248, in load_scripts
script_module = script_loading.load_module(scriptfile.path)
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/script_loading.py", line 11, in load_module
module_spec.loader.exec_module(module)
File "frozen importlib._bootstrap_external>", line 846, in exec_module
File "frozen importlib._bootstrap_external>", line 983, in get_code
File "frozen importlib._bootstrap_external>", line 913, in source_to_code
File "frozen importlib._bootstrap>", line 228, in _call_with_frames_removed
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/prompt_chatgpt.py", line 123
match precision_dropdown:
^
SyntaxError: invalid syntax

I erased <

this happened...
i tried to solve it myself.. but it's out of my control, i think
i'm completely blind at python and computer science.. so sorry for asking you to help me again
can you help me?

Perhaps create a drop down in the UI for users to select the model?
For those of us with access, gpt-4 is available and your extension works with it.
https://platform.openai.com/docs/models/gpt-4

When I tell ChatGPT to create an image, it receives it just fine, but when it finishes creating the image, I got an error.

Many times I get this error: Exception: ChatGPT answers doesn't match batch count. Got 32 answers, expected 30

Sorry, but this is very annoying error. When it happens user needs to wait few minutes until it times out. I don't really care if it gives me 30 or 32 answers, roughly is okay, just don't make me restart it again 🙈🙈

make it easy to save a template and enter to see prompt and send to buttons please.

Hi,
thanks for this extension, it is really great.

I like a chrome extension "AIPRM for ChatGPT", search "Stable Diffusion"， there are many Stable Diffusion prompt generators, the first one is:
https://app.aiprm.com/prompts/1786396703751139328/stable-diffusion-prompt-based-of-your-idea

it's really good, could we integrated it to sdwebui?

I have been using ChatGPT in China, but it tends to be very unstable. Is it possible to add an option for a custom API domain? This would be greatly appreciated. Thank you.

Got this message (also it uses GPT3.5 even if I have GPT4.0):

You tried to access openai.ChatCompletion, but this is no longer supported in openai>=1.0.0 - see the README at https://github.com/openai/openai-python for the API.

You can run `openai migrate` to automatically upgrade your codebase to use the 1.0.0 interface.

Alternatively, you can pin your installation to the old version, e.g. `pip install openai==0.28`

A detailed migration guide is available here: https://github.com/openai/openai-python/discussions/742

I've tried batch count but it only repeat one prompt for multiple times.
What is I would like to generate 200+ different photos automatically?

Hello,

When using the extension, I run into an Attribution error: "module 'openai' has no attribute 'ChatCompletion'". I know ChatGPT ran some updates and Completion is now a legacy function (on their playground). I am not a developer or coder, I hope this issue is solvable since I enjoy the extension very much.
I run SD through google colabs and use the A1111 interface. I tried reinstallation with no success. Full Error message (sorry for the length, ADetailer is turned off but adds a lot of text):

**__ChatGPT request:
I want you to act as a prompt generator. Compose each answer as a visual sentence. Do not write explanations on replies. Format the answers as javascript json arrays with a single string per answer. Return exactly 1 to my question. Answer the questions exactly. Answer the following question:
Make a color description

ChatGPT query failed. Retrying. Error: module 'openai' has no attribute 'ChatCompletion'
ChatGPT request:
I want you to act as a prompt generator. Compose each answer as a visual sentence. Do not write explanations on replies. Format the answers as javascript json arrays with a single string per answer. Return exactly 1 to my question. Answer the questions exactly. Answer the following question:
Make a color description

ChatGPT query failed. Retrying. Error: module 'openai' has no attribute 'ChatCompletion'
ChatGPT request:
I want you to act as a prompt generator. Compose each answer as a visual sentence. Do not write explanations on replies. Format the answers as javascript json arrays with a single string per answer. Return exactly 1 to my question. Answer the questions exactly. Answer the following question:
Make a color description

ChatGPT query failed. Retrying. Error: module 'openai' has no attribute 'ChatCompletion'
ChatGPT request:
I want you to act as a prompt generator. Compose each answer as a visual sentence. Do not write explanations on replies. Format the answers as javascript json arrays with a single string per answer. Return exactly 1 to my question. Answer the questions exactly. Answer the following question:
Make a color description
Return exactly 1 answers to my question.

*** Error completing request
*** Arguments: ('task(cgbd5neqncdemzo)', '', '', [], 36, 'DPM++ 2M SDE Karras', 1, 1, 7, 1280, 1024, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x7f5c9b07fa00>, 5, False, '', 0.8, -1, False, -1, 0, 0, 0, False, {'ad_model': 'face_yolov8n.pt', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'inpaint_global_harmonious', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, {'ad_model': 'None', 'ad_prompt': '', 'ad_negative_prompt': '', 'ad_confidence': 0.3, 'ad_mask_k_largest': 0, 'ad_mask_min_ratio': 0, 'ad_mask_max_ratio': 1, 'ad_x_offset': 0, 'ad_y_offset': 0, 'ad_dilate_erode': 4, 'ad_mask_merge_invert': 'None', 'ad_mask_blur': 4, 'ad_denoising_strength': 0.4, 'ad_inpaint_only_masked': True, 'ad_inpaint_only_masked_padding': 32, 'ad_use_inpaint_width_height': False, 'ad_inpaint_width': 512, 'ad_inpaint_height': 512, 'ad_use_steps': False, 'ad_steps': 28, 'ad_use_cfg_scale': False, 'ad_cfg_scale': 7, 'ad_use_checkpoint': False, 'ad_checkpoint': 'Use same checkpoint', 'ad_use_vae': False, 'ad_vae': 'Use same VAE', 'ad_use_sampler': False, 'ad_sampler': 'DPM++ 2M Karras', 'ad_use_noise_multiplier': False, 'ad_noise_multiplier': 1, 'ad_use_clip_skip': False, 'ad_clip_skip': 1, 'ad_restore_face': False, 'ad_controlnet_model': 'None', 'ad_controlnet_module': 'inpaint_global_harmonious', 'ad_controlnet_weight': 1, 'ad_controlnet_guidance_start': 0, 'ad_controlnet_guidance_end': 1, 'is_api': ()}, <scripts.animatediff_ui.AnimateDiffProcess object at 0x7f5c9b0549d0>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x7f5c9b00b340>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x7f5c9b0561a0>, <scripts.controlnet_ui.controlnet_ui_group.UiControlNetUnit object at 0x7f5c9b0a0250>, None, False, '0', '0', 'inswapper_128.onnx', 'CodeFormer', 1, True, 'None', 1, 1, False, True, 1, 0, 0, False, 0.5, None, False, '0', '/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/models/roop/inswapper_128.onnx', 'CodeFormer', 1, '', 1, 1, False, True, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, False, None, None, False, None, None, False, None, None, False, 50, 'Make a color description', 2, 1.0, True, '', '', True, False, False, False) {}
Traceback (most recent call last):
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/modules/call_queue.py", line 57, in f
res = list(func(*args, **kwargs))
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/modules/call_queue.py", line 36, in f
res = func(*args, **kwargs)
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/modules/txt2img.py", line 52, in txt2img
processed = modules.scripts.scripts_txt2img.run(p, args)
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/modules/scripts.py", line 601, in run
processed = script.run(p, script_args)
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/prompt_chatgpt.py", line 141, in run
chatgpt_answers = get_chatgpt_answers(chatgpt_prompt, int(chatgpt_batch_count), temperature, original_prompt)
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/chatgpt_answers.py", line 30, in get_chatgpt_answers
chatgpt_answers = retry_query_chatgpt(prompt, prompt_count, temperature, 4)
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/chatgpt_utils.py", line 18, in retry_query_chatgpt
raise e
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/chatgpt_utils.py", line 12, in retry_query_chatgpt
chatgpt_answers = query_chatgpt(messages, count, temperature, is_last_retry)
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/chatgpt_utils.py", line 39, in query_chatgpt
chat_gpt_response = get_chat_completion([
File "/content/drive/MyDrive/AI_PICS/stable-diffusion-webui/extensions/stable-diffusion-webui-chatgpt-utilities/scripts/chatgpt_utils.py", line 63, in get_chat_completion
completion = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=messages, temperature=temperature)
AttributeError: module 'openai' has no attribute 'ChatCom_pletion'_

我想通过API模式 使用此扩展。可以告诉我在/sdapi/v1/txt2img 中如何传此扩展参数吗。谢谢

Hi,

I installed it in my stable diffusion and set the api key in the settings but whe i try to generate something give me all this errors!

Chat GPT request:
I want you to act as a prompt generator. Compose each answer as a visual sentence. Do not write explanations on replies. Format the answers as javascript json arrays with a single string per answer. Return exactly 4 to my question. Answer the questions exactly. Answer the following question:
Describe an epic d&d scene using the prompt ""a warlock man with a hero look"" as inspiration. Describe the person, clothing/armor and atmosphere. Don´t use any name or artist names from the original prompt. Give me 8 examples with unique characteristics. Return only a short description.

Error completing request
Arguments: ('task(w7qqill1xjysrzo)', 'a warlock man with a hero look', '', [], 20, 15, False, False, 1, 1, 4.5, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 6, False, True, False, 0, -1, False, '', False, False, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'LoRA', 'None', 1, 1, 'Refresh models', False, True, False, 'none', 'None', 1, None, False, 'Scale to Fit (Inner Fit)', False, False, 64, 64, 64, 0, 1, False, False, 'none', 'None', 1, None, False, 'Scale to Fit (Inner Fit)', False, False, 64, 64, 64, 0, 1, False, False, False, False, False, '1:1,1:2,1:2', '0:0,0:0,0:1', '0.2,0.8,0.8', 20, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0, None, None, 50, 'Describe an epic d&d scene using the prompt "{prompt}" as inspiration.\nDescribe the person, clothing/armor and atmosphere.\nDon´t use any name or artist names from the original prompt.\nGive me 8 examples with unique characteristics.\nReturn only a short description.', 4.0, False, '', '', False, False, False, 0, 0, 512, 512, False, False, True, True, True, False, False, 1, False, False, 2.5, 4, 0, False, 0, 1, False, False, 'u2net', False, False, False, False) {}
Traceback (most recent call last):
File "F:\SD\stable-diffusion-webui\extensions\stable-diffusion-webui-chatgpt-utilities\scripts\chatgpt_utils.py", line 10, in retry_query_chatgpt
chatgpt_answers = query_chatgpt(messages, count)
File "F:\SD\stable-diffusion-webui\extensions\stable-diffusion-webui-chatgpt-utilities\scripts\chatgpt_utils.py", line 26, in query_chatgpt
chat_gpt_response = get_chat_completion([
File "F:\SD\stable-diffusion-webui\extensions\stable-diffusion-webui-chatgpt-utilities\scripts\chatgpt_utils.py", line 52, in get_chat_completion
completion = openai.ChatCompletion.create(model="gpt-3.5-turbo", messages=messages, temperature=0.5)
File "F:\SD\stable-diffusion-webui\venv\lib\site-packages\openai\api_resources\chat_completion.py", line 25, in create
return super().create(*args, **kwargs)
File "F:\SD\stable-diffusion-webui\venv\lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
File "F:\SD\stable-diffusion-webui\venv\lib\site-packages\openai\api_requestor.py", line 226, in request
resp, got_stream = self._interpret_response(result, stream)
File "F:\SD\stable-diffusion-webui\venv\lib\site-packages\openai\api_requestor.py", line 619, in _interpret_response
self._interpret_response_line(
File "F:\SD\stable-diffusion-webui\venv\lib\site-packages\openai\api_requestor.py", line 679, in _interpret_response_line
raise self.handle_error_response(
openai.error.RateLimitError: You exceeded your current quota, please check your plan and billing details.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "F:\SD\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "F:\SD\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "F:\SD\stable-diffusion-webui\modules\txt2img.py", line 53, in txt2img
processed = modules.scripts.scripts_txt2img.run(p, *args)
File "F:\SD\stable-diffusion-webui\modules\scripts.py", line 376, in run
processed = script.run(p, *script_args)
File "F:\SD\stable-diffusion-webui\extensions\stable-diffusion-webui-chatgpt-utilities\scripts\prompt_chatgpt.py", line 110, in run
chatgpt_answers = retry_query_chatgpt(chatgpt_prompt, int(chatgpt_batch_count), 3)
File "F:\SD\stable-diffusion-webui\extensions\stable-diffusion-webui-chatgpt-utilities\scripts\chatgpt_utils.py", line 12, in retry_query_chatgpt
if (len(chatgpt_answers) == count):
UnboundLocalError: local variable 'chatgpt_answers' referenced before assignment