UmeAiRT - FLUX Workflow MEGAPACK
Here you will find all my workflows for FLUX. The easiest way is to copy this folder to ComfyUI\user\default\workflows.
What's included :
TXT to IMG
IMG to IMG
INPAINT
OUTPAIN
KONTEXT
ControlNet (OPENPOSE/HED/CANNY/DEPTH)
Upscaler
LoRA tester
IMG to TXT
Resources you need:
📂Files for "base" version :
Model : flux1-dev-fp8.safetensors or flux1-dev-fp16.safetensors
in ComfyUI\models\diffusion_models
FILL Model : flux1-fill-dev-fp8.safetensors or flux1-fill-dev-fp16.safetensors
in ComfyUI\models\diffusion_models
KONTEXT Model : flux1-kontext-dev-fp8-e4m3fn.safetensors
in ComfyUI\models\diffusion_models
CLIP : clip_l.safetensors
in ComfyUI\models\clip
📂Files for GGUF version :
Model : Q8, Q6, Q5, Q4, Q3
in ComfyUI\models\unet
FILL Model : Q8, Q6, Q5, Q4, Q3
in ComfyUI\models\unet
KONTEXT Model : G8, G5, G4
in ComfyUI\models\unet
CLIP : Q8, Q6, Q5, Q4, Q3
in ComfyUI\models\clip
📂Files for NUNCHAKU version :
Model : svdq-int4_r32-flux.1-dev.safetensors
in ComfyUI\models\diffusion_models
FILL Model : svdq-int4_r32-flux.1-fill-dev.safetensors
in ComfyUI\models\diffusion_models
KONTEXT Model : svdq-int4_r32-flux.1-kontext-dev.safetensors
in ComfyUI\models\diffusion_models
📂Common Files
Text encoder : t5xxl_fp8_e4m3fn.safetensors or ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors
VAE : ae.safetensors
in ComfyUI\models\vae
ANY upscale model :
Realistic : RealESRGAN_x4plus.pth
Anime : RealESRGAN_x4plus_anime_6B.pth
in ComfyUI\models\upscale_models
📦Custom Nodes :
Description
Completely reworked version, fewer modules needed, new UI and compatible with the latest version of ComfyUI.