Cascade plus SDXL
created a year ago
42 nodes

2.8k

389

Credits
inspired by a conversation with NeuraLunk
Outputs
example image output optimized_comfy_workflows_user_uploads/95c90df6-45e8-4b7a-b08c-d5a8f6164637/assets/verevolf.webp for workflow.
Description

This workflow allows you to create larger scale SDXL images by using Cascade as the base renderer then running a refinement pass through an SDXL model. It also improves fine details and clutter found in the original Cascade render.

Built-in nodes
StableCascade_EmptyLatentImage
StableCascade_StageB_Conditioning
Custom nodes
CLIPLoader
VAELoader
KSampler
ConditioningZeroOut
VAEDecode
CLIPTextEncode
CR Prompt Text
VAEEncode
BboxDetectorSEGS
UltralyticsDetectorProvider
FreeU
DetailerForEach
CR Image Output
CascadeResolutions
CheckpointLoaderSimple
UNETLoader
Seed Everywhere
Models
0
0
1
0