If you liked my workflow, please give it a like.
It's easy for you, and I'm pleased.
Pony1/Pony2/XL1 versions were optimized for the Lightning lora
Pony3, XL2-XL4, Photo1-2 and Insta1 versions were optimized for the DMD2 lora.
Both speed up rendering by a factor of 3-6x and let Big Love produce more photorealistic results.
Version 2.0
My completely redesigned workflow.
Added an upscaling toggle.
4 Resolution options.
Added ControlNet to the workflow, which is activated when a character's pose needs to be transferred from a reference image. You can choose the ControlNet type; the default is Auto.
The refiner uses a prompt that gets added on to the base prompt.
Refining Prompt+Positive Prompt.
It is recommended that the Refining Prompt end with a comma and a space. (, )
Version 1.0
This is a modernized workflow from the author of the Big Love Checkpoint model. All image resolution and sampler settings are identical to those in the workflows provided by the author of SubtleShader in the description of his model.
Added easy integration of LoRA.
Added quick switching of the generated image orientation (vertical or horizontal).
Added tooltips with links to the models and LoRA used in the workflow.
txt2img Settings:
More Realistic & Faster Rendering:
Good Quality: For more contrast add the SDXL Lightning 8-step lora with DPM++ SDE, SGM Uniform, 8 steps, cfg 1.5-3 (Pony), 1-2.5 (XL/Photo), lora strength 1.0, clip skip 2, 832x1216 or 1024x1496
Best Quality: For a more natural look use the DMD2 lora with LCM Exponential, 8 steps, cfg 1 (Photo/XL4), 1-1.5 (Others), lora strength 1.0, clip skip 2, 832x1216 or 1024x1496
Upscaling:
1. txt2img with Lightning 8-step lora: Hires fix, 4x_NMKD-Superscale-SP_178000_G upscaler, 3 hires steps, 0.4 denoise, 1.5x, hires cfg 2, clip skip 2
Higher Quality & Faster Rendering:
Good Quality: img2img with Lightning 8-step lora: same prompt, DPM++ SDE, SGM Uniform, 1.25-1.5x (XL), 1.5-2x (Pony), 3 steps (ComfyUI), 6-8 steps (Pony), 4-12 steps (XL/Photo), cfg 2, lora strength 1.0, 0.3-0.5 denoise, clip skip 2
Best Quality: img2img with DMD2 lora: same prompt, LCM Exponential, 1.25-1.5x (XL/Photo), 1.5-2x (Pony), 8-12 steps (XL1/XL2) 4-8 steps (XL2.5-XL4/Photo), cfg 1, lora strength 1.0, 0.3-0.5 denoise, clip skip 2