Archive

A very simple workflow using KSampler with several previews, highres, upscale and face swap.Designed for "point and shoot" people like me that don't want to have over the top w...

Workflow I use to create the preview images on my models here on Civitai. It creates the metadata that's compatible with the site's resource tagging so you get accurate info on...

? If you find this workflow helpful please consider liking it and following me for more awesome stuff like this in the future! ?Try this workflow for free on RunComfyThis is th...

1枚の画像に異なる2人のキャラクターを生成するComfyUIのサンプルワークフローです,生成からUltimateSDUpscaleによるアップスケールまで対応しています,ご自由にカスタマイズしてお使いくだ...

注意！注意！！！此工作流只适用于二次元图片，因为其中的yolov8-seg模型是我专门针对二次元训练的,工作流原理：yolo模型检测图中文字、花体字、对话框、拟声词等部分，据此创建蒙版，然后...

1枚の画像に異なる2人のキャラクターを生成するComfyUIのサンプルワークフローです,生成からUltimateSDUpscaleによるアップスケールまで対応しています,ご自由にカスタマイズしてお使いくだ...

V5 - Added Latent Noise Injection section to the workflow - Improves the quality and details of the imageAdded the power lora loader back in for ease of useThe Red Nodes are th...

--- v2.0 has 3 LoRA spots, Save Image with Metadata, Optional Upscale and just More Neat than the quick share ---Quick share for those who ask in comments, it's about this mode...

This is a basic workflow for flux.1 Dev. Everything except models needed should work fne in the manager. Read below for model links.`Features:First passHiresfixSecond pass refi...

Run flux with negative prompting via 2 different methods in ComfyUI. Tested on a 16GB RTX A4000 and the fp8 dev model. Affects performance dramatically - approx 2x slower with ...

V5 - Added Latent Noise Injection section to the workflow - Improves the quality and details of the imageAdded the power lora loader back in for ease of useThe Red Nodes are th...

Generate Multi Prompts with Flux.1-Dev and Lora realism + SD UpscaleYou can found the Lora Here:https://huggingface.co/comfyanonymous/flux_RealismLora_converted_comfyui ...

This is a workflow for detailing and restoring using SUPIR. Should work in 10gb (barely).removed all images because civit marks simple anime as x rated for no reason nowModels:...

V5 - Added Latent Noise Injection section to the workflow - Improves the quality and details of the imageAdded the power lora loader back in for ease of useThe Red Nodes are th...

Run flux with negative prompting via 2 different methods in ComfyUI. Tested on a 16GB RTX A4000 and the fp8 dev model. Affects performance dramatically - approx 2x slower with ...

--- v2.0 has 3 LoRA spots, Save Image with Metadata, Optional Upscale and just More Neat than the quick share ---Quick share for those who ask in comments, it's about this mode...

v2_FLUX_D_model_Q8_clip_Q8v2_FLUX_D_model_Q8_clip_Q8_IMG_TO_MGv2_FLUX_D_model_Q8_clip_Q8_LORA.v2_FLUX_D_model_Q8_clip_Q8_LORA_IMG_TO_MGComparison T5xx fp16 to Q8 - almost the s...

Just Released ControlNet Union for SDXL1 Model Does it All (Pose, Canny, Scribble... and so on).No more need to hold onto so many different Controlnet Models.Choose witch prepr...

Remember to read the instruction!Please use Pixel version, if you don't have good understanding on Latent version.This will provide youCrazzzzzzzzzzzzzzzzzzzzzzzzzzzzzyAmazzzzz...

Remember to read the instruction!Please use Pixel version, if you don't have good understanding on Latent version.This will provide youCrazzzzzzzzzzzzzzzzzzzzzzzzzzzzzyAmazzzzz...