python - Diffusers pipeline Instant ID with Ipadapter - Stack Overflow

admin管理员组

文章数量:1122832

I want to use an implementation of InstantID with Ipadapter using Diffusers library. So far I got :

import diffusers
from diffusers.utils import load_image
from diffusers.models import ControlNetModel
from transformers import CLIPVisionModelWithProjection


# Custom diffusers implementation Instantid & insightface 
from insightface.app import FaceAnalysis
from pipeline_stable_diffusion_xl_instantid import StableDiffusionXLInstantIDPipeline, draw_kps

# Other dependencies
import cv2
import torch
import numpy as np
from PIL import Image

from compel import Compel, ReturnedEmbeddingsType


app_face = FaceAnalysis(name='antelopev2', root='./', providers=['CPUExecutionProvider', 'CPUExecutionProvider']) #CUDAExecutionProvider
app_face.prepare(ctx_id=0, det_size=(640, 640))

# prepare models under ./checkpoints
face_adapter = "./models/instantid/ip-adapter.bin"
controlnet_path = "./models/instantid/ControlNetModel/"

# load IdentityNet
controlnet = ControlNetModel.from_pretrained(controlnet_path, torch_dtype=torch.float16)
pipe = StableDiffusionXLInstantIDPipeline.from_single_file(
    "./models/checkpoints/realvisxlV40_v40LightningBakedvae.safetensors", 
    controlnet=controlnet, torch_dtype=torch.float16

)
pipe.cuda()

# load adapter
pipe.load_ip_adapter_instantid(face_adapter)

# Load ipadapter
image_encoder = CLIPVisionModelWithProjection.from_pretrained(
    "./models/ipadapters",
    subfolder="sdxl_models/image_encoder",
    torch_dtype=torch.float16,
    #weight_name="ip-adapter-plus_sdxl_vit-h.safetensors"
).to("cuda")

# Apply adapter to pipe
pipe.image_encoder = image_encoder

pipe.load_ip_adapter("./models/ipadapters", subfolder="sdxl_models", weight_name="ip-adapter-plus_sdxl_vit-h.safetensors")
pipe.set_ip_adapter_scale(1.3)

# Optimisation
pipe.enable_model_cpu_offload()
pipe.enable_vae_tiling()

image = Image.open("img1.png")

face_info = app_face.get(cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR))
face_info = sorted(face_info, key=lambda x:(x['bbox'][2]-x['bbox'][0])*(x['bbox'][3]-x['bbox'][1]))[-1]  # only use the maximum face
face_emb = face_info['embedding']


prompt = "prompt"

kps = Image.open("kps_standard.png")

ipadapter_image = Image.open("img2.png")

#encod = pipe.image_encoder(ipadapter_image)


prompt_embed, pooled = compel_proc(prompt)

image = pipe(
    prompt,

    width=768,
    height=1024,

    image_embeds=face_emb,
    image=kps,
    seed=42,
    ip_adapter_image=ipadapter_image,
    
    controlnet_conditioning_scale=0.7,
    control_guidance_end = .7,
    num_inference_steps=6,
    guidance_scale=3,
    
).images[0]

And got :

ValueError: <class 'diffusers.models.unet_2d_condition.UNet2DConditionModel'> has the config param `encoder_hid_dim_type` set to 'ip_image_proj' which requires the keyword argument `image_embeds` to be passed in  `added_conditions`

Thus I tried to implement image_embeds:

pipe(...,     added_conditions={"image_embeds": face_emb}, ..)

or added_conditions="image_embeds", added_cond_kwargs = { "image_embeds" : face_emb},

Tested on:

Windows 10

Python=3.10

Diffusers=0.28

transformers=4.40.2

torch=2.3.0

peft=0.0.11.1.

The environment can run instantid and ipadapter generation on different pipeline, but not on the same.

本文标签： pythonDiffusers pipeline Instant ID with IpadapterStack Overflow