With this, you can get the faces you've grown to love, while benefiting from the highly detailed SDXL model. To add to the customizability, it also supports swapping between SDXL models and SD 1.5 models. Switch back and forth to test your prompts with the "CLIP Type" switch.Įver generate an amazing image, only to have the face be sub-par? With the Face Detailer extension, you can swap that face out with a new one! This extension has it's own positive and negative prompts, as well as seed and sampler, so you can tweak it until it's just right. This workflow gives you the choice to use the SDXL prompt style or the original SD prompt style. This has has some benefits, namely cleaner and simpler prompts, but it's not for everyone. With the release of SDXL 0.9 and subsequently 1.0, we were introduced to "text_g" and "text_l", which are two separate ways of handling prompt inputs. 2x, 3x, 4x, you can do it all! This uses a tiled approach to upscaling, where each tile is the original txt2img resolution. With the Ultimate SD Upscaler, you can push your images to much higher resolution without needing a supercomputer to run it. It can be a bit heavy on resource utilization at higher resolutions, but will create beautiful generations. This is the traditional way to upscale images, and can be helpful to increase the details while upscaling. Not only is it easy to use, but leads to far less confusion than other "switches" built into ComfyUI. With a new toggle-based system, you can change what runs and how it runs in seconds. This ControlNet will apply to the module when generating the output image. You can also adjust the strength, start percent, and end percent. You can standardize the seed across all the modules or use separate seeds per moduleįixed incorrect linkage for img2img Face Detailer (was using txt2img output)Īdded LoRA / Lycoris support for Face DetailerĮvery module has it's own ControlNet section, where you can copy/paste the preprocessed image and select the type of ControlNet you are looking to run. The FaceDetailer module is now the AfterDetailer module and supports all the above Module based, making it easier to understand what's going onĭraw custom masks or use the segmentation model to auto-generate masks for your selected areas Major overhaul to the design of the workflow Support for loading outside images for upscalingįixed bug where it would always regenerate images even when it didn't need to Support for both SDXL Base-only and Base + Refiner flows Replaced image aspect ratio selector to support custom sizes Just run the extractor-v3.2.exe included in the zip file to use itĪdded img2img generation as optional input to Ultimate SD Upscalerįixed alternative VAE selector (0 = base | 1 = alternative) Pick a style to influence your generationsĭrag-and-drop your image to view the prompt details and save it in A1111 format so CivitAI can read the generation details Please show him some support and check out his other great AI/ML and Art based videos!Ĭome join me in my Discord server to ask any questions you may have, make suggestions for future versions of this workflow, or post your creations! ImpactFrames has done an outstanding job showing some of the different features of this workflow and walking you through a short getting started tutorial.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |