Hydra-v54 SDXL to Cascade
5.0
0 reviews
Description
video: https://youtu.be/htQgbTqIiLQ
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.
Discussion
(No comments yet)
Loading...
Reviews
No reviews yet
Versions (1)
- latest (2 years ago)
Node Details
Primitive Nodes (55)
Image scale to side (2)
Integer (2)
Note (13)
PrimitiveNode (20)
Reroute (18)
Custom Nodes (42)
- CR Apply LoRA Stack (1)
- CR Multi-ControlNet Stack (2)
- CR Apply Multi-ControlNet (1)
- CR LoRA Stack (1)
ComfyUI
- PreviewImage (6)
- ImageScaleToTotalPixels (1)
- CLIPTextEncode (2)
- VAEDecode (2)
- KSampler (2)
- StableCascade_StageB_Conditioning (1)
- ConditioningZeroOut (1)
- CheckpointLoaderSimple (3)
- LoadImage (2)
- VAELoader (1)
- ModelSamplingStableCascade (1)
- CLIPTextEncodeSDXL (2)
- CLIPSetLastLayer (1)
- VAEEncode (1)
- StableCascade_StageC_VAEEncode (1)
- SaveImage (2)
- KSamplerAdvanced (1)
- ImageResize+ (1)
- MiDaS-DepthMapPreprocessor (1)
- OpenposePreprocessor (1)
- ScribblePreprocessor (1)
- CannyEdgePreprocessor (1)
- ColorCorrect (1)
- ReActorFaceSwap (1)
Model Details
Checkpoints (3)
RealVisXL_V3.0.safetensors
stable_cascade_stage_b.safetensors
stable_cascade_stage_c.safetensors
LoRAs (3)
ZenkaiXL-v0.2.safetensors
kzkAnimeThorra-V2-XL_C3Lier-LR3E3-000001.safetensors
xvx-style-XL-000001.safetensors