Synthartx SDXL Workflow


Updated:

Workflow Preview

Showcases (Image/Video)

It takes around 80 seconds for a generation using the LOW_VRAM configuration on a RTX 5080(16 GB VRAM), 64 GB OF RAM

It takes around 380 seconds for a generation using the HIGH_VRAM configuration on a RTX 5080(16 GB VRAM), 64 GB OF RAM

Load any checkpoint you want, but I used janku 7.77 for my generations. Please note that different models have different cfgs, samplers, and schedulers. I've left them easily configurable in the processing suit.

You are free to use my set of loras, but if you have your own than you can change them in the lora manager.

My set of Loras -

<lora:AddMicroDetails_Illustrious_v5:0.35>, <lora:Dramatic Lighting Slider:1.00>, <lora:outline_xl_end:-1.00>, <lora:MOON-NSFW:0.40>, <lora:E7BBAAE584BF20E58E9AE6B682E69E84E59BBE.gkED:0.60>, <lora:Rella-000195:0.80>

My newest set of loras -

lora:AddMicroDetails_Illustrious_v6:0.35> <lora:MOON-NSFW:0.40> <lora:E7BBAAE584BF20E58E9AE6B682E69E84E59BBE.gkED:0.25> <lora:748cm_c_illu:0.30> <lora:USNR_STYLE_ILL_V1_lokr3-000024:0.80> <lora:Dramatic Lighting Slider:1.00> <lora:Rella-000195:0.60> <lora:Create Concept (Style) Illustrious:0.40> <lora:style_strength_controller_illus01_v1:0.40>

E7BBAAE584BF20E58E9AE6B682E69E84E59BBE.gkED -> [Style filter] Xu Er thick paint composition light texture enhancement

In the Load Model Subgraph

You can change the Width, Height, and Batch Size (how many generations at once)

Your positive prompt is the top box

Your negative prompt is the bottom box

KS Pass 1 is Ksampler 1-

60 steps recommended - 15 steps minimum

dpmpp_3m_sde_gpu recommended - Euler A minimum

karras recommended - simple minimum

Detailer

120 steps recommended - 15 steps minimum

dpmpp_3m_sde_gpu recommended - Euler A minimum

karras recommended - simple minimum

Iterative Upscale

3 iterative steps recommended - 2 iterative steps minimum

dpmpp_3m_sde_gpu recommended - Euler minimum

karras recommended - simple minimum

3x upscale factor recommended - 1.5x minimum

10 steps recommended - 8 steps minimum

0.35 denoise recommended - 0.2 minimum

You are free to choose what image saver you want, I just put the basic one.

Extra notes-

Iterative upscale is quite heavy, so you can just bypass it if your computer can't handle it.The results of Kspass 1 and detailer are already good if you can set that higher.

Thank you for using my workflow, ask me for any questions

Nodes Detail

49 Nodes
Primitive Node Types
0
Custom Node Types
49
  • GetNode25
  • SetNode11
  • 1b02424f-aa41-45eb-820c-a5f49699cbfc1
  • Seed (rgthree)1
  • Image Comparer (rgthree)2
  • SaveImage1
  • 6f99278a-762f-4cc1-9302-9213df0da0be1
  • 591a7c9b-89f5-48e3-aa24-064a743f08481
  • 89aa0f29-2cb1-403d-8ba6-8fca1b4c2bbc1
  • CheckpointLoaderSimple1
  • CLIPSetLastLayer1
  • Lora Loader (LoraManager)1
  • TriggerWord Toggle (LoraManager)1
  • Note1