Extremely simple and intuitive workflow for FLUX models.I really hate all of the nodes, lines, colors..... so... Idea was to put together very simple workflow, without confusin...

A workflow to explore the flux1.s output as a latent image, and use the SDXL to refine it, upscale it, and detail it to the final image.On the KSampler (Efficient), feel free t...

Flux Split SigamsUpscaleDetailing For cleaner more detailed images.Empty Latent Size PickerFlorence 2 Prompting to help get Prompting from images you like.Group Bypasser to tur...

Revolutionary ComfyUI Workflow: Integrating Gemini and Ollama for Professional Prompt GenerationA few hours ago I was developing my node https://github.com/al-swaiti/ComfyUI-Ol...

Uses my custom dictionary loaders and text appender nodes in combination with an LLM prompt enhancement geared towards FLUX's detailed natural language training.If you have tro...

See GitHub page for more details.OverviewI've created an All-in-One FluxDev workflow in ComfyUI that combines various techniques for generating images with the FluxDev model, i...

Special Note: RGBA mode will not work with all nodes, you will need RGB. RGBA is for something I'm doing, but it will work with a lot of nodes, but you are better off using RGB...

Lightning-fast image generation with a Tiny Flux Schnell setup that delivers results in just 3 seconds (on a 4090*). For even higher resolution, the optional UltimateSDUpscale ...

NF4 is significantly faster and more memory-efficient than FP8 due to its use of native bnb.matmul_4bit, which avoids casting and leverages low-bit CUDA tricks. It achieves bet...

Clip-lfor GGUF t5 modelsOFFICIAL gguf modelsadvance gguf workflowMY UNIQUE EDITION modelMY MERGE *** remember the gguf format not depend that much on GPU so the Q8 is the most ...

A simple workflow for FLUX including Controlnet.In this workflow I have put three types of model loaders, chekpoint loader NF-4 with option to change Clip, Chekpoint Loader and...

Uses my custom dictionary loaders and text appender nodes in combination with an LLM prompt enhancement geared towards FLUX's detailed natural language training.If you have tro...

Allows negative prompting for flux. Simple workflow, easy to integrate into any other workflow. Fully tested, behaviors and best practices included in notes.Negative Prompt Beh...

Flux Florence Fun: Pic Remixer with automatic prompting, restyling, and CLIP Optimization!This will take an input image, automatically describe it, restyle it however you'd lik...

Vision Realistic Flux dev fp8 描述: 训练词语: 名称: ...

Clip-lfor GGUF t5 modelsOFFICIAL gguf modelsadvance gguf workflowMY UNIQUE EDITION modelMY MERGE *** remember the gguf format not depend that much on GPU so the Q8 is the most ...

to kijai GitHub - kijai/ComfyUI-ControlNeXt-SVDmodel:视频转绘 模型链接:https://pan.quark.cn/s/cd19ce050f4a提取码:a91d 描述: to kijai GitHub - kijai/ComfyUI-...

This is a ComfyUI workflow for Flux dev + Flux schnell merge.Just a simple workflow to get 'good enough' gens from Flux, using only 10 steps.0) You should already have 'T5xxl' ...

VERSION 8.0:SDXL 1.0Deforum Video Creation Workflow.DDPMVERSION 5.0 Onwards:SDXL 1.0Deforum Video Creation Workflow.DPM++ SDE KarrasPerfect for use with ZavyChromaXL Checkpoint...

You want to use Flux, check out this workflowAutomatic_ComfyUI_SDXL+Flux_Base_Modul_Styler_ - v0.82 | Stable Diffusion Workflows | CivitaiVideo to Version full v0.81without flu...
由于网站升级,部分用户密码全部设置为111111,登入后自己修改, 并且VIP等级提升一级(包月提升至包季,包季提升到包年 包年提升至永久)
没有账号?注册  忘记密码?

社交账号快速登录