Fashion Image Generation版本v1.0 (ID: 465522)

This workflow allows you to load images of an AI Avatar's face, shirt, pants, shoes, pose and generates a fashion image based on your prompt. This workflow chains together multiple IPAdapters, which allows you to change each piece of the AI Avatar's clothing individually.

Models Required

1) Your favourite SD1.5 checkpoint. Download and place in models/checkpoints

2) IPAdapter Models. I am asking you to install more than what is required so that if you change some of the options, it will still work. If you are getting errors, you will have to install the exact model that you are missing.

• Clip Vision. CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors and CLIP-ViT-bigG-14-laion2B-39B-b160k.safetensors. Install using the manager, search for "clip".

• ip-adapter_sd15.safetensors, ip-adapter_sd15_light.safetensors, ip-adapter_sd15_vit-G.safetensors, ip-adapter-plus_sd15.safetensors. Install using the manager, search for "ipadapter"

• ip-adapter-plus-face_sd15.safetensors, ip-adapter-full-face_sd15.safetensors,ip-adapter-faceid_sd15.bin, ip-adapter-faceid-plus_sd15.bin. Install using the manager, search for "ipadapter"

4) Openpose Controlnet Model. control_v11p_sd15_openpose_fp16.safetensors. Install using the manager, search for "controlnet"

Instructions on how to use the Workflow

1) Load images of your AI Avatar's face, shirt, pants and shoes

2) Load the same image of the pose into the pose, face mask, shirt mask, pants mask and shoes mask nodes.

3) In the face mask, shirt mask, pants mask and shoes mask nodes, right click the picture and select "Open in Mask Editor" and mask the relevant portions of the image. This will guide the IPAdapter to apply the pictures to the correct parts of the generated image.

4) Click "Queue Prompt"

Modifying the Workflow

1) I am using Iterative Upscale, you can replace this part of the workflow with your favourite upscaler (HiRes Fix /Supir /Ultimate SD Upscale)

描述:

训练词语: