Add IPAdapter advanced weighting [Instant Style]

[huchenlei]

Closes #2749.

SDXL composition [instant style]

Infotext:

1girl, absurdres, highres, (masterpiece:1.2), (best quality, highest quality),
Negative prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green
Steps: 40, Sampler: DPM++ 2M, Schedule type: Karras, CFG scale: 7, Seed: 1058757959, Size: 1000x1000, Model hash: aeb7e9e689, Model: juggernautXL_v8Rundiffusion, Clip skip: 2, ControlNet 0: "Module: ip-adapter-auto, Model: ip-adapter_sdxl [d5d53548], Weight: 1, Resize Mode: Crop and Resize, Low Vram: False, Processor Res: 512, Threshold A: 0.5, Threshold B: 0.5, Guidance Start: 0, Guidance End: 1, Pixel Perfect: False, Control Mode: Balanced, Hr Option: Both, Save Detected Map: True", Version: v1.9.0-15-gff6f4680

SDXL style transfer [instant style]

Infotext:

1girl, absurdres, highres, (masterpiece:1.2), (best quality, highest quality),
Negative prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, deformed cat, deformed, photo, anthropomorphic cat, monochrome, photo, pet collar, gun, weapon, blue, 3d, drones, drone, buildings in background, green
Steps: 40, Sampler: DPM++ 2M, Schedule type: Karras, CFG scale: 7, Seed: 1058757959, Size: 1000x1000, Model hash: aeb7e9e689, Model: juggernautXL_v8Rundiffusion, Clip skip: 2, ControlNet 0: "Module: ip-adapter-auto, Model: ip-adapter_sdxl [d5d53548], Weight: 1, Resize Mode: Crop and Resize, Low Vram: False, Processor Res: 512, Threshold A: 0.5, Threshold B: 0.5, Guidance Start: 0, Guidance End: 1, Pixel Perfect: False, Control Mode: Balanced, Hr Option: Both, Save Detected Map: True", Version: v1.9.0-15-gff6f4680

Free edit on weights

You can also freely adjust any weight number by directly editing the weight array.

API usage

Just set advanced_weighting field in the API to control weight on each block with cross attention. You can refer to scripts/ipadapter/weight.py for weight presets used on the UI.

{
  "image": realistic_girl_face_img,
  "module": "ip-adapter-auto",
  "model": "ip-adapter_sd15",
  "advanced_weighting": [1, 1, 1, ..., 1],
}