Hydra-v54 SDXL to Stable Cascade
created a year ago
img2img
lora
controlnet
face
97 nodes

377

59

Outputs
example image output 0 for workflow.
example image output 1 for workflow.
example image output 2 for workflow.
example image output 3 for workflow.
example image output 4 for workflow.
example image output 5 for workflow.
example image output optimized_comfy_workflows_user_uploads/96cd9226-e767-4dff-b29b-a3e2990eeb55/assets/hydra-cascade_00154_.webp for workflow.
Description

video: https://youtu.be/htQgbTqIiLQ

Hydra is a workflow series with a single goal, allowing any model to be used with Cascade. Although this is strictly impossible, we can approximate using SDXL Control Nets then pass images into Clip Vision for Cascade.

Hydra-v54 (medium sized)

- based on v43, Simplified for speed.

- combined prompt & image input

- SDXL uses ControlNets

(reduced custom nodes)

SDXL benefits from Controlnet and lora so you can create a spread of images to prime the Cascade generation. With careful prompting and a good input image, all you need to do is alter the denoise on the Stage C node.

•light = 0.3

•mid = 0.5

•heavy = 0.7

try sending an output into the Cascade to get even closer to an SDXL output, or mix prompts and images to experiment blending the same input image in cascade.

Built-in nodes
StableCascade_StageB_Conditioning
ModelSamplingStableCascade
StableCascade_StageC_VAEEncode
Custom nodes
CR Apply LoRA Stack
PreviewImage
ImageScaleToTotalPixels
MiDaS-DepthMapPreprocessor
ColorCorrect
PrimitiveNode
OpenposePreprocessor
CLIPTextEncode
VAEDecode
KSampler
ConditioningZeroOut
CheckpointLoaderSimple
LoadImage
CR Multi-ControlNet Stack
VAELoader
CLIPTextEncodeSDXL
CLIPSetLastLayer
CR Apply Multi-ControlNet
VAEEncode
ImageResize+
ScribblePreprocessor
CannyEdgePreprocessor
CR LoRA Stack
SaveImage
ReActorFaceSwap
KSamplerAdvanced
Models
0
0
0
0