Other

Resolution for txt2img: 768x512.ControlNet settings:Preprocessor: none Model: canny.Control mode: ControlNet is more important. 描述: 训练词...

Credit:This script package from bdsqlszuse kohya-ss/sd-scripts (github.com) for coreoriginal script from Akegarasu/lora-scripts: LoRA training scripts use kohya-ss's trainer, f...

Credit:This script package from bdsqlszuse kohya-ss/sd-scripts (github.com) for coreoriginal script from Akegarasu/lora-scripts: LoRA training scripts use kohya-ss's trainer, f...

CLIPTextEncode Node with BLIPDependenciesFairscale>=0.4.4 (NOT in ComfyUI)Transformers==4.26.1 (already in ComfyUI)Timm>=0.4.12 (already in ComfyUI)Gitpython (already in ...

Yes we can use a slide in PowerPoint as OpenPose editor. The benefit is not only that we don't need to go online or install an extension, but that PowerPoint doesn't restrict a...

Updated 21.3.:Support for multiple input files addedExtended sample range to 10 000 by defaultTool that helps with selecting a random amount of prompts from a file that contain...

Updated 21.3.:Support for multiple input files addedExtended sample range to 10 000 by defaultTool that helps with selecting a random amount of prompts from a file that contain...

Recently, I've introduced the konyconi style LoRA tutorial (https://civitai.com/models/52697/tutorial-konyconi-style-lora)The most annoying and frustrating step in it is:STEP 4...

IntroIn this model has all the character, can achieve higher pitch. Gotou Futari is the cutest voice and able produce higher output quality even just 10 files at ~10 seconds ea...

IntroIn this model has all the character, can achieve higher pitch. Gotou Futari is the cutest voice and able produce higher output quality even just 10 files at ~10 seconds ea...

IntroIn this model has all the character, can achieve higher pitch. Gotou Futari is the cutest voice and able produce higher output quality even just 10 files at ~10 seconds ea...

IntroIn this model has all the character, can achieve higher pitch. Gotou Futari is the cutest voice and able produce higher output quality even just 10 files at ~10 seconds ea...

SD1.5 + SDXL Base shows already good results. SD1.5 + SDXL Base+Refiner is for experiment onlySD1.5 + SDXL Base - using SDXL as composition generation and SD 1.5 for final work...

SD1.5 + SDXL Base shows already good results. SD1.5 + SDXL Base+Refiner is for experiment onlySD1.5 + SDXL Base - using SDXL as composition generation and SD 1.5 for final work...

This is templates pack intended for segmentation method in ControlNet. It won't give you actual comic but you can use it with other methods and/or inpaint to make something lik...

---[update]---added some micro feature that helps me preparing dataset a bit fastercreate captions files from that contain a simple trigger word and the sub-folder namezipping ...

---[update]---added some micro feature that helps me preparing dataset a bit fastercreate captions files from that contain a simple trigger word and the sub-folder namezipping ...

---[update]---added some micro feature that helps me preparing dataset a bit fastercreate captions files from that contain a simple trigger word and the sub-folder namezipping ...

This is a Windows tool that can capture images for control nets using the vrm, glb, and gltf models.The tool itself Selling, reprinting, etc. is prohibited. Selling images crea...

This is a Windows tool that can capture images for control nets using the vrm, glb, and gltf models.The tool itself Selling, reprinting, etc. is prohibited. Selling images crea...