Model: "HAL": Hellocomic (25) + Addictivefuture (50) + LeviR36 (25)

Sampling Method: PLMS

denoising Strength: 0.75

512x800 & 2x Hires fix = 1024x1600

Use with or without ControlNet

CFG Scale: 11

Sampling Steps: 40

Upscaler: 8X_NMKD-Superscale_150000

VAE: vae-ft-mse-840000-ema-pruned.wae.pt

Clip Skip: 2

****After extensive testing, I have found that images created in ComfyUI have occasional facial defects and minor skin abnormalities. However, you can take an image from ComfyUI and put it in A1111 img2img. Select "Just resize (latent upscale)", sampling method "Euler a", sampling steps: 20, restore faces: true, width: same as input (1024),height: same as input (1600),****CFG Scale:1****,Denoising strength:0.15 and leave the prompts blank then A1111 will correct the defects in the face and skin, and also adjust the coloring. It sharpens the face but smooths out other details a little. That being said, this is the best damn model I've seen yet!

Check out more sample images: https://www.deviantart.com/naraphim