Flux IMG2IMG with LoRas and Wildcards
created 8 months ago
img2img
lora
inpainting
27 nodes

2.3k

390

Credits
ComfyUI Impact (node for Wildcard use)
Outputs
example image output 0 for workflow.
example image output 1 for workflow.
example image output 2 for workflow.
example image output optimized_comfy_workflows_user_uploads/f07577c9-e206-49f2-8f12-55752ef7d7f6/assets/ComfyUI_00071_.webp for workflow.
Description

IMG2IMG using the full Flux difference model with 2 LoRas and 2 prompt inputs - one is used for wildcards to add some variety.

Dimensions have to be changed in two places, but if enough people like this I'll make it work with just a single input.

Built-in nodes
RandomNoise
SamplerCustomAdvanced
BasicGuider
EmptySD3LatentImage
ModelSamplingFlux
FluxGuidance
Custom nodes
DualCLIPLoader
LoraLoader
KSamplerSelect
VAELoader
ConditioningCombine
VAEDecode
ImageToMask
UNETLoader
VAEEncodeForInpaint
LatentComposite
SaveImage
PrimitiveNode
ImpactWildcardEncode
CLIPTextEncode
ImageScale
LoadImage
BasicScheduler
0
0
0
0