2023-09-21 17:25:20
High fidelity image enlargement? ? Ultra HD lossless? Full of details? – StableSR…….StableSR plug-in installation & related model download Step 1: Install the StableSR plug-in. Regarding plug-in expansion installation, please refer to the previous article: AI Drawing-Stable Diffusion 007- Installation, update, removal and backup of plug-in expansion Extensions Step 2 : Download the model file. After the StableSR installation is completed, we also need to download the Checkpoints model file & StableSR module required to operate StableSR and put it into the corresponding folder before we can start using it. Checkpoints model (Stable Diffusion V2.1 768 EMA checkpoint (~5.21GB)): Download from the HuggingFace website: Download the HuggingFace file and put it in the folder path: …….modelsStable-diffusionStableSR module (webui_768v_139.ckpt): Download from the HuggingFace website: Download the HuggingFace_StableSR Module file and put it in the folder path: …….extensionssd-webui-stablesrmodels Step 3: Download other plug-ins or VAE models that are officially recommended for use (optional, not necessary) StableSR Operation Interface & Usage Setting Precautions After completing all installations and downloading the required model files, you will see an additional StableSR option SR Model in the Script under the graph function page: Here it is The previously downloaded StableSR module – webui_768v_139.ckptScale Factor: Image magnification factor. (After enabling StableSR, the image size settings in other places will be invalid) Color Fix: When using StableSR and divided drawing (ex. Tiled Diffusion), it is easy to cause color shift, so Color Fix needs to be turned on. There are a total of 2 options (Wavelet, AdaIN). The official website here recommends using the Wavelet algorithm for better results. Pure Noise: When Pure Noise is turned on, SD will ignore the redraw range and ultimately generate a more detailed picture. When Pure Noise is not turned on, even if the redraw amplitude is set to the maximum value of 1, the final image will not fully reach the original detail presentation of the redraw amplitude of 1 (this may be more ideal for the imaging effect in terms of aesthetics), and in When Pure Noise is not turned on, the official recommendation is to set the redraw amplitude to 1. Operation notes/suggestions: Please note that Checkpoint should choose the specified large model, and although SD VAE does not necessarily need to be provided by the official website, since the official website provides another one, choose the one recommended by the official website. It is recommended to use the sampling method (Sampling method) of the graph: Euler a, CFG Scale=7, Sampling steps (Sampling steps) >= 20. The actual measurement recommendations of the official website, plus Negative prompts will help improve the imaging quality (ex. 3d, cartoon , anime, sketches, (worst quality:2), (low quality:2)), and positive prompts (Prompts) are not very helpful, but they may have some effect (ex. (masterpiece:2), (best quality) :2), (realistic:2), (very clear:2)) When the generated image size is > 512, it is recommended to use Tiled Diffusion & VAE, otherwise the imaging quality will deteriorate. (It will really get worse… Tiled Diffusion & VAE is a must-use combination at all, right?) (For information on how to install and use Tiled Diffusion & VAE, please refer to the previous article: AI Drawing-Stable Diffusion 016- Tiled Diffusion with Tiled VAE) When used with StableSR, the official recommendations for Tiled Diffusion settings are as follows: Method = Mixture of Diffusers: Latent tile size = 96, Latent tile overlap = 48 Latent tile batch size: The bigger the better, as long as the video memory is not exceeded. Select “none” for the Upscaler (because there is no need to zoom in here, the zooming operation will be performed at StableSR). After all settings are completed, put the image into the plot window and start calculating the image ~ StableSR image enlargement actual measurement hell Yes, I have set it up according to the parameters on the official website. The instructions found on the Internet also have the same settings. The only difference is that I use real-life photos instead of two-dimensional or 2.5D animated photos. But what regarding the “high-fidelity” amplification that was promised? , Ultra high definition lossless? Full of details? This plug-in also says Suitable for most images (Realistic or Anime, Photography or….) Oh, forget it, I have spent time installing/downloading some model files to be paired, so I’d better record the results and uninstall, install and delete them later. , don’t waste space and increase the burden of SD operation. 512×768 4x magnification: It’s only 4x magnification. I thought 2x would be enough. I zoomed in a little bit at a time, but the result was not much different, except that the realistic photo became very flat, and then the picture was full of grain. Textures/artifacts/various small areas of bad painting….. PS. 512×768 Magnified 4 times, if it is not paired with Tiled Diffusion with tiled VAE, it will look like this: Finally, I am really curious whether the effect will be different according to the two-dimensional/2.5D animation pictures everyone uses for teaching: Using two-dimensional When I try the pictures, the effect is not as terrible as the real-life photos, but it is not as good as amazing. StableSR requires more downloaded files and settings, and the result is not better… (Comparison of the pictures below) Enlarge the original image 768×768 4 times (3072×3072). The detailed effect will be better if the Pure Noise effect is enabled than if the Denoising setting 1 is not enabled.) Well, the StableSR plug-in uses all the parameter settings recommended by the official website. There is a problem. There are a lot of them, and I am too lazy to spend more time doing more parameter adjustment tests. If anyone tries it out and gets better results in the future, if possible, please kindly tell me what the problem is~~~
1695341125
#DrawingStable #Diffusion #Highfidelity #image #enlargement #StableSR
