Workflows

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...

Generic added with works with everything 'except' Flux.Latest version adds the civitai metadata (including Lora's). Also, to add 40 punk styles for use with the styler, see thi...

4.0 bug: If you have more than one male or female face, use 3.0.This is optimized for speed. The steps are lower because it is not nessesary to have them as high as people usua...

FLUX-Capacitor by pAInCREAT0RI am not a professional COMFYUI workflow builder. In fact, I only recently started experimenting in COMFYUI (transitioning from A111). I spend more...

Finally v1.I needed to see where the industry was going before I went with a version 1.This uses Flux.1-Dev GGUF Q2.K Q3.KS Q4 and I did many tests. This can produce PRO levels...

04/12/2024 - Fixed Bug with "NAN" in image saver mode since last ComfyUI release.This ComfyUI Workflow takes a Flux Dev model image and gives the option to refine it with an S...