Sampling Steps for each outpaint: 20 Outpainting tab Magical scene, dazzling glow, 8k, intricate, elegant, highly detailed, majestic, digital photography, art by artgerm and ruan jia and greg rutkowski, hdr I found it produces better results when you have a gradual transition of the subject We will use the style in the common part of the prompt.Ĭommon Prompt Prefix: (leave empty) Start at secondīeautiful woman, shining eyes, yellow hair, in temple We will use the subject in the middle, variable part of the prompt. Magical scene, shining eyes, dazzling glow, 8k, intricate, elegant, highly detailed, majestic, digital photography, art by artgerm and ruan jia and greg rutkowski, hdr The subject part of the initial prompt is We keep the same style throughout the video. This can be changed at any time point, defined in the table. Let’s break the prompt of the initial image into two parts: Now you know you can have a fixed and variable part in the prompt. Similar to the prefix, all frames use the same prompt suffix. Common Prompt Suffix: Ending part of the prompt.This can be changed at any different time in the video. This is common to all frames of the video. Common Prompt Prefix: Beginning part of the prompt.This extension breaks the prompt into 3 parts: Total video length is the total length of the video. Main tabīatch Count is the number of videos you are going to make each time you press the Generate button. Go to the Infinite Zoom page in AUTOMATIC1111. (Note: BadDream is a negative embedding for DreamShaper.) Stable Diffusion checkpoint: DreamShaper 8 Modelīeautiful woman, yellow hair, in temple, magical scene, shining eyes, dazzling glow, 8k, intricate, elegant, highly detailed, majestic, digital photography, art by artgerm and ruan jia and greg rutkowski, hdr.For example, use the DreamShaper 8 model to create the initial image and the DreamShape 8 inpainting model to create the infinite zoom video. You should use a pairing model to generate the first image for the best result. It is not the best because an inpainting model is trained to fill in a missing part of an image, not directly creating one. We used the inpainting model in the previous example to generate the initial image. Now you have verified that your setup is working, let’s go through a slightly more advanced example. Now, you use the new prompt for inpainting.Īnd you get the idea. The process repeats itself until you reach 2 sec, where you switch to the next prompt. ![]() The extension inpaints the empty space using the same prompt. ![]() Now, you have created a small frame of empty space around the shrunk image. In the next frame, the initial image is shrunk slightly to create the illusion of zooming out. So, the initial image is generated with the prompt at time 0 using the inpainting model. The subject is written in the prompt and has changed at 2 sec, 3 sec, and 5 sec. The prompt of the initial image is a combination of the common prefix, prompt, and the common suffix. Now, it’s a good time to pause and understand what happened. We will explain them later, but the Prompt Start at second is the prompt that is switched to at that time.Īfter a brief wait, you should get a video like this. You should see the Common Prompt Prefix, the Prompt Start at second, the Common Prompt Suffix, and the Negative Prompt populated with the default values. Step 3: Review settings and press generate Select the inpainting model in the Stable Diffusion checkpoint dropdown menu. Download the model file and put it in the folder: stable-diffusion-webui\models\Stable-diffusion Step 2: Select the inpainting model Let’s use the Dreamshaper Inpainting model. You should use an inpainting model for a reasonable result. You can use this quick example to test your setup and ensure everything works correctly. Wait for the confirmation message that the installation is complete. ![]() Enter the following URL in the URL for extension’s git repository field. Installing Infinite Zoom on Windows or MacĤ. If you use our Colab Notebook, enter the following URL in the Extensions_from_URL field. You will need to install the infinite zoom extension in AUTOMATIC1111. You can use this GUI on Windows, Mac, or Google Colab.Ĭheck out the Quick Start Guide if you are new to Stable Diffusion.Ĭheck out the AUTOMATIC1111 Guide if you are new to AUTOMATIC1111. It is a popular and free open-source software. We will use AUTOMATIC1111 Stable Diffusion WebUI to create infinite zoom videos. Step 4: Convert to animated GIF (Optional). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |