About
This is the scalar presented by @philz1337x where he combines MultiDiffusion, ControlNet tiles and details LoRas to obtain an interesting upscalar similar to Magnific's AI. The purpose of this article is to simply illustrate his technique when using Automatic1111
Steps
Switch to img2img
Enter positive and negative prompts
masterpiece, best quality, highres, <lora:more_details:0.7> <lora:SDXLrender_v2.0:1>
(worst quality, low quality, normal quality:2) JuggernautNegative-neg
Use the following settings
Steps: 18
Sampler: DPM++ 3M SDE Karras
CFG Scale: 6
Size: 1024x1024
Model: juggernaut_reborn
Denoising Strength: 0.35Enable Tiled Diffussion, configure as follows
Upscalar: 4x-UltraSharp
Tiled Diffusion: MultiDiffusion
Tile tile width: 112
Tile tile height: 144
Tile Overlap: 4
Tile batch size: 8
Upscale factor: 2
Keep input size: true
(https://github.com/pkuliyi2015/multidiffusion-upscaler-for-automatic1111)Enable ControlNet 0, configure as follows
Module: tile_resample
Model: control_v11f1e_sd15_tile
Weight: 0.6
Resize Mode: 1
Low VRam: False
Pixel Perfect: TrueDrop an image on img2img
Start with a 768x768 image, this process is memory hungry.
Generate