The first step is downloading the text encoder files if you don't have them already from SD3, Flux or other models: (clip_l.safetensors, clip_g.safetensors and t5xxl) if you don't have them already in your ComfyUI/models/clip/ folder. For the t5xxl I recommend t5xxl_fp16.safetensors if you have more than 32GB ram or t5xxl_fp8_e4m3fn_scaled.safetensors if you don't.
The sd3.5_large.safetensors file (put it in your ComfyUI/models/checkpoints/ directory) does not contain text encoder/CLIP weights so you must load them separately to use that file just like in the following example:
To use the sd3.5_large_turbo.safetensors file (put it in your ComfyUI/models/checkpoints/ directory) you can use the above example and set steps to 4 and cfg to 1.2.
For convenience there is an easy to use all in one checkpoint file sd3.5_large_fp8_scaled.safetensors (put it in your ComfyUI/models/checkpoints/ directory) that can be used in the default workflow like any other checkpoint files.
See this workflow for an example.
As a reminder you can save these image files and drag or load them into ComfyUI to get the workflow.