This version has functional nodes, but it does not switch prompts due to a bug on TensorArt. SDXL model is used as an example here
FromToSteps-v2
Workflow Preview
Showcases (Image/Video)

Showcases (Image/Video)

Nodes Detail
11 NodesPrimitive Node Types
8- SaveImage1
- VAEDecode1
- CLIPTextEncode3
- EmptyLatentImage1
- KSampler1
- CheckpointLoaderSimple1
Custom Node Types
3- ConditioningSetTimestepRange2
- ConditioningBlend1