TypeError: IPAdapter.__init__() got an unexpected keyword argument 'target_blocks'
ahmadmustafaanis opened this issue · comments
Ahmad Mustafa Anis commented
code:
import torch
from diffusers import StableDiffusionXLPipeline
from PIL import Image
from ip_adapter import IPAdapterXL
base_model_path = "stabilityai/stable-diffusion-xl-base-1.0"
image_encoder_path = "sdxl_models/image_encoder"
ip_ckpt = "sdxl_models/ip-adapter_sdxl.bin"
device = "cuda"
# load SDXL pipeline
pipe = StableDiffusionXLPipeline.from_pretrained(
base_model_path,
torch_dtype=torch.float16,
add_watermarker=False,
)
pipe.enable_vae_slicing() # for low mem
# load ip-adapter
# target_blocks=["blocks"] for original IP-Adapter
# target_blocks=["up_blocks.0.attentions.1"] for style blocks only
# target_blocks = ["up_blocks.0.attentions.1", "down_blocks.2.attentions.1"] # for style+layout blocks
ip_model = IPAdapterXL(pipe, image_encoder_path, ip_ckpt, device, target_blocks=["up_blocks.0.attentions.1"])
image = "frame.jpg"
image = Image.open(image)
image.resize((512, 512))
# generate image variations with only image prompt
images = ip_model.generate(pil_image=image,
prompt="a cat, masterpiece, best quality, high quality",
negative_prompt= "text, watermark, lowres, low quality, worst quality, deformed, glitch, low contrast, noisy, saturation, blurry",
scale=1.0,
guidance_scale=5,
num_samples=1,
num_inference_steps=30,
seed=42,
#neg_content_prompt="a rabbit",
#neg_content_scale=0.5,
)
images
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
[<ipython-input-3-75dc3a052ac8>](https://localhost:8080/#) in <cell line: 24>()
22 # target_blocks=["up_blocks.0.attentions.1"] for style blocks only
23 # target_blocks = ["up_blocks.0.attentions.1", "down_blocks.2.attentions.1"] # for style+layout blocks
---> 24 ip_model = IPAdapterXL(pipe, image_encoder_path, ip_ckpt, device, target_blocks=["up_blocks.0.attentions.1"])
25
26 image = "frame.jpg"
TypeError: IPAdapter.__init__() got an unexpected keyword argument 'target_blocks'
InstantX commented
Are you using our code? We make some minimum modifications on original IP-Adapter codebase.
g711ab commented
我也遇到了同样的问题,需要卸载tencent-ailab/IP-Adapter?还是用ip-adapter中的文件替换?
InstantX commented