├── __init__.py ├── .gitignore ├── requirements.txt ├── realtime_i2i.py ├── README.md ├── capture.py ├── lcm.py ├── config.py └── LICENSE /__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__/* -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tori29umai0123/LCM_i2i_PoC/HEAD/requirements.txt -------------------------------------------------------------------------------- /realtime_i2i.py: -------------------------------------------------------------------------------- 1 | from config import ConfigWindow 2 | 3 | config = ConfigWindow() 4 | config.open() 5 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # LCM_i2i_PoC 2 | LCM-LoRAを用いた高速i2iの検証用リポジトリ 3 | 4 | # 使い方 5 | （Windows環境での実行を想定） 6 | 7 | 以下のライブラリが使用できるようにセットアップ 8 | - cv2 9 | - numpy 10 | - pygetwindow 11 | - pyautogui 12 | - diffusers 13 | - pyTorch 14 | - PIL 15 | - pynput 16 | - tkinter 17 | 18 | PowerShellでrealtime_i2i.pyを実行 19 | 20 | 生成結果の表示画面が表示されたら、i2iしたい画面をクリック。 21 | 22 | # 使用例 23 | 24 | 25 | https://github.com/mattyamonaca/LCM_i2i_PoC/assets/48423148/69509251-286e-4c80-aaf1-bb1807749dd4 26 | 27 | # おまけ 28 | 細かい仕組みや使い方はこちら 29 | https://zenn.dev/mattyamonaca/articles/3875b6e7f066d3 30 | 31 | -------------------------------------------------------------------------------- /capture.py: -------------------------------------------------------------------------------- 1 | from pynput import mouse 2 | from PIL import ImageGrab 3 | 4 | import tkinter as tk 5 | 6 | class ScreenCapture: 7 | 8 | def __init__(self): 9 | self.root = tk.Tk() 10 | self.root.attributes('-fullscreen', True) 11 | self.root.attributes('-topmost', True) 12 | self.root.attributes('-alpha', 0.5) 13 | self.root.configure(bg='white') 14 | self.root.bind('', lambda e: self.root.quit()) 15 | 16 | self.start_position = None 17 | self.selection = None 18 | 19 | def on_click(self, x, y, button, pressed): 20 | if pressed: 21 | self.start_position = (x, y) 22 | self.selection = tk.Canvas(self.root, cursor="cross", bg='black') 23 | self.selection.place(x=x, y=y, width=1, height=1) 24 | else: 25 | self.root.quit() 26 | 27 | def on_drag(self, x, y): 28 | if self.start_position: 29 | self.selection.place_configure(width=max(1, x - self.start_position[0]), height=max(1, y - self.start_position[1])) 30 | 31 | 32 | def capture(self): 33 | screenshot = ImageGrab.grab(bbox=(self.x0, self.y0, self.x1, self.y1)) 34 | #screenshot = ImageGrab.grab(bbox=(self.start_position[0], self.start_position[1], self.end_position[0], self.end_position[1])) 35 | return screenshot 36 | 37 | 38 | def listen(self): 39 | # マウスリスナーの開始 40 | listener = mouse.Listener(on_click=self.on_click, on_move=self.on_drag) 41 | listener.start() 42 | 43 | self.root.mainloop() 44 | listener.stop() 45 | self.x0, self.y0 = self.start_position 46 | self.x1, self.y1 = self.selection.winfo_x() + self.selection.winfo_width(), self.selection.winfo_y() + self.selection.winfo_height() 47 | -------------------------------------------------------------------------------- /lcm.py: -------------------------------------------------------------------------------- 1 | 2 | 3 | import cv2 4 | import numpy as np 5 | import pygetwindow as gw 6 | 7 | from diffusers import AutoPipelineForImage2Image, UNet2DConditionModel, LCMScheduler 8 | from diffusers.utils import load_image 9 | import torch 10 | from PIL import Image 11 | import pygetwindow as gw 12 | 13 | 14 | def get_pipe(config): 15 | pipe = AutoPipelineForImage2Image.from_pretrained( 16 | config.generation_model_name.get(), torch_dtype=torch.float16, use_safetensors=True 17 | ).to("cuda") 18 | 19 | 20 | pipe.load_lora_weights(config.lcm_model_name.get()) 21 | pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config) 22 | 23 | if pipe.safety_checker is not None: 24 | pipe.safety_checker = lambda images, **kwargs: (images, [False]) 25 | 26 | return pipe 27 | 28 | 29 | def LCM_run(config, pipe): 30 | cv2.namedWindow("Window Capture", cv2.WINDOW_NORMAL) 31 | config.running = True 32 | while config.running: 33 | # アクティブなウィンドウを取得 34 | screenshot = config.screen_capture.capture() 35 | img_np = np.array(screenshot) 36 | 37 | generator = torch.Generator("cuda").manual_seed(2500) 38 | #img = cv2.cvtColor(img_np, cv2.COLOR_BGR2RGB) 39 | img = Image.fromarray(img_np) 40 | 41 | 42 | img = pipe( 43 | strength=config.strength_value, 44 | prompt=config.prompt.get(), 45 | image=img, 46 | num_inference_steps=config.num_inference_steps_value, 47 | guidance_scale=1, 48 | generator=generator 49 | ).images[0] 50 | 51 | # PILイメージをnumpy配列に変換 52 | img = np.array(img) 53 | 54 | # OpenCVでは色の順番がBGRなので、RGBからBGRに変換 55 | img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR) 56 | 57 | # キャプチャした画像を同じウィンドウで更新して表示 58 | cv2.imshow("Window Capture", img) 59 | 60 | # 'q'を押したらループを抜ける 61 | if cv2.waitKey(1) & 0xFF == ord('q'): 62 | break 63 | 64 | 65 | 66 | cv2.destroyAllWindows() 67 | 68 | -------------------------------------------------------------------------------- /config.py: -------------------------------------------------------------------------------- 1 | from diffusers.utils import load_image 2 | import tkinter as tk 3 | from tkinter import ttk 4 | import threading 5 | 6 | from lcm import get_pipe, LCM_run 7 | from capture import ScreenCapture 8 | 9 | class ConfigWindow: 10 | def __init__(self): 11 | master = tk.Tk() 12 | self.run_thread = None 13 | self.running = False 14 | self.master = master 15 | master.title("Configuration") 16 | master.geometry("400x500") # ウィンドウサイズを設定 17 | 18 | 19 | style = ttk.Style() 20 | style.configure("TLabel", font=("Arial", 12)) 21 | style.configure("TEntry", padding=5) 22 | style.configure("TButton", padding=5, font=("Arial", 10)) 23 | 24 | # LCMモデル名 25 | ttk.Label(master, text="LCMモデル名").grid(row=0, column=0, padx=10, pady=10, sticky="w") 26 | self.lcm_model_name = tk.StringVar(value="latent-consistency/lcm-lora-sdv1-5") 27 | ttk.Entry(master, textvariable=self.lcm_model_name, width=30).grid(row=0, column=1, padx=10, pady=10) 28 | 29 | # 生成モデル名 30 | ttk.Label(master, text="生成モデル名").grid(row=1, column=0, padx=10, pady=10, sticky="w") 31 | self.generation_model_name = tk.StringVar(value="852wa/SDHK") 32 | ttk.Entry(master, textvariable=self.generation_model_name, width=30).grid(row=1, column=1, padx=10, pady=10) 33 | 34 | # プロンプト 35 | ttk.Label(master, text="プロンプト").grid(row=2, column=0, padx=10, pady=10, sticky="w") 36 | self.prompt = tk.StringVar() 37 | ttk.Entry(master, textvariable=self.prompt, width=30).grid(row=2, column=1, padx=10, pady=10) 38 | 39 | # strength 40 | ttk.Label(master, text="strength").grid(row=3, column=0, padx=10, pady=10, sticky="w") 41 | self.strength = tk.StringVar(value=0.75) 42 | ttk.Entry(master, textvariable=self.strength, width=30).grid(row=3, column=1, padx=10, pady=10) 43 | 44 | # num_inference_steps 45 | ttk.Label(master, text="num_inference_steps").grid(row=4, column=0, padx=10, pady=10, sticky="w") 46 | self.num_inference_steps = tk.StringVar(value=8) 47 | ttk.Entry(master, textvariable=self.num_inference_steps, width=30).grid(row=4, column=1, padx=10, pady=10) 48 | 49 | 50 | #画面キャプチャ 51 | capture_button = ttk.Button(master, text="キャプチャ開始", command=self.capture_screen) 52 | capture_button.grid(row=5, column=0, columnspan=2, padx=10, pady=10, sticky="ew") 53 | 54 | #パラメータ更新 55 | capture_button = ttk.Button(master, text="パラメータ更新", command=self.update_param) 56 | capture_button.grid(row=6, column=0, columnspan=2, padx=10, pady=10, sticky="ew") 57 | 58 | def update_param(self): 59 | self.num_inference_steps_value = int(self.num_inference_steps.get()) 60 | self.strength_value = float(self.strength.get()) 61 | 62 | 63 | def capture_screen(self): 64 | if self.run_thread is not None: 65 | self.running = False 66 | self.run_thread.join() 67 | 68 | self.screen_capture = ScreenCapture() 69 | self.screen_capture.listen() 70 | self.screen_capture.root.destroy() 71 | self.update_param() 72 | pipe = get_pipe(self) 73 | 74 | self.running = True 75 | self.run_thread = threading.Thread(target=LCM_run, args=(self, pipe)) 76 | self.run_thread.start() 77 | 78 | 79 | def open(self): 80 | self.master.mainloop() 81 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | --------------------------------------------------------------------------------