Workflow name: sd3.5 model + SUPIR HD enlargement and repair
[Workflow introduction]
This workflow requires you to upload an image you like at the image loading location, and then the prompt words will be inferred through Runninghub captioner, combined with the sd3.5 model text image, and given to the sampler, and then the SUPIR model HD enlargement and repair will be used to generate a HD image.

[Usage scenario]
You can experience this process immediately by just uploading an image, try your favorite style options, and create a unique image effect! Try it now

[Key nodes]
Runninghub Captioner

[Model version]
sd3.5
Model name: sd3.5_large.safetensors
SUPIR
Model name: SUPIR v0Q.ckpt

[LoRA model]
None

[ControlNet application]
None

[K sampler]
CFG: 5.5
Sampling method: euler
Scheduler: sgm uniform
Noise reduction: 1