![]() ![]() We need lower value because the face is not too bad. Send the new image to inpainting and creates a mask on her face.ĭenoising strength: 0.2. This is something inpainting is very suitable for fixing. Using the same settings (denoising strength 0.75, original content) and after generating about 16 images, I picked the following image Fixing the face Repaint the mask but only covering the sneaker. You will need to use the undo button at top right to completely remove the mask. We will follow similar steps: select the bottom right image and use Send to Inpaint button to send it to the inpaint canvas on the left.Īgain, on the inpaint canvas, you would found nothing has changed. Let’s say we want to change the sneaker she wears. When inpainting to fix limbs or anything, you should start with a large area, and progressively move on to smaller ones. The new 4 are generated based on the improved image above.īottom right is a clear winner. Using the same mask and the same parameters, hit Generate button to get another 4. ![]() But because we want to reuse the same mask, we are not going to do that. You will see the changes if you remove the mask. The reason is all the changes are under the masked area which are covered by the black paint. To use a image for the next round, you select the image in the right canvas and use Send to inpaint button under the image to send it to the inpainting canvas.Īfter pressing the button, you may wonder why nothing seemed to have changed. In case you see no improvements, you can regenerate another set of 4. Although not perfect, let’s pick the top left image because it moves to the right direction. So it’s important to generate multiple images and pick the best one. You can see the newly generated images are with varying degree of success. Use the paintbrush tool next to the inpainting canvas to create a mask around the legs. Let’s fix the legs first because they are the most problematic. Now, we are ready to use inpainting to fix the limbs. Select the Stable Diffusion v1.5 inpainting model. This is important as you want to generate something different over each trials. Increase if you want to it to change more. It is useful for painting finer details like faces.īatch size: Set to a reasonable number like 4 so that you can cherry pick the best one.ĭenoising strength is a very important parameter. “ Only masked” paints the masked area only but with higher resolution. Inpaint area: “ Whole picture” generates images coherent with the whole image. Sample step: Set to a value reasonably high, like 25. Inpainting parametersīelow is the screenshot of my inpainting setting. Regardless of the method you use, now you should have setup the GUI like below. Upload the image by dragging and dropping to the image canvas. ![]() Write the prompt and negative prompt in the corresponding input boxes. Use the convenient Send to Inpaint button under the image to send a newly generated image to inpainting.Īlternative, if you are using the downloaded image, go to img2img tab and select the Inpaint sub-tab. We will fix this image with inpainting alone. ![]() This image was generated using the txt2img tab in AUTOMATIC1111. Obviously the legs are the most problematic. You can download this image using the button below if you want to follow this tutorial. We will fix the following image with distorted limbs. We will use the same prompt in the inpainting example. The two images to be fixed were generated using the following prompt.įull-body portrait of beautiful female wearing running outfit, highlights in hair, sitting outside restaurant, brown eyes, wearing a dress, side lightĭisfigured, ugly, bad, immature, two heads You can use any other photo editing software. I will use Photoshop to paint over certain areas in the second example. Make sure to check the inpainting model when launch the colab notebook in the Quick Start Guide.įollow the instructions to install the inpainting model if you run AUTOMATIC1111 locally. You can also install it on Windows and Mac. You can run this GUI with 1-click using the Colab notebook in the Quick Start Guide. I will use AUTOMATIC1111 GUI in this tutorial. Example 1: Inpainting only to fix limbs. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |