philz1337x / clarity-upscaler

Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative
https://ClarityAI.co
GNU Affero General Public License v3.0
3.58k stars 371 forks source link

What are the right steps to use these parameters on sd webui? #12

Closed gin063 closed 5 months ago

gin063 commented 5 months ago

I think something went wrong in one of the steps, I found that the effect is very different from your demonstration. prompt: masterpiece, best quality, highres, Negative prompt: (worst quality, low quality, normal quality:2) JuggernautNegative-neg Steps: 18, Sampler: DPM++ 3M SDE Karras, CFG scale: 6, Seed: 1337, Size: 792x1000, Model hash: 338b85bc4f, Model: juggernaut_reborn, Denoising strength: 0.35, Tiled Diffusion upscaler: 4xUltrasharp_4xUltrasharpV10, Tiled Diffusion scale factor: 2, ControlNet 0: "Module: tile_resample, Model: control_v11f1e_sd15_tile [a371b31b], Weight: 0.6, Resize Mode: 1, Low Vram: False, Processor Res: 512, Threshold A: 1, Threshold B: 1, Guidance Start: 0, Guidance End: 1, Pixel Perfect: True, Control Mode: 1, Hr Option: HiResFixOption.BOTH, Save Detected Map: True", Lora hashes: "more_details: 3b8aa1d351ef, SDXLrender_v2.0: 3925cf4759af", Version: v1.8.0

image image image

model: juggernaut_reborn loras: more_details, SDXLrender embeddings: JuggernautNegative-neg extensions: Tiled Diffusion controlnet model: control_v11f1e_sd15_tile

gin063 commented 5 months ago

It looks like my generated data is different from yours:

  1. I don't have the following in my data: {"Method": "MultiDiffusion", "Tile tile width": 112, "Tile tile height": 144, "Tile Overlap": 4, "Tile batch size": 8, "Upscaler": "4x-UltraSharp", "Upscale factor": 2, "Keep input size": true}
  2. Save Detected Map: False", mine is "true".