KeyError: 'proj.weight'

#19
by sleepy-chrisy - opened

Hi,

I am using diffusers==0.24.0 and trying to run this sample from the release 0.24.0 on colab
https://github.com/huggingface/diffusers/releases/tag/v0.24.0

''''
from diffusers import DiffusionPipeline, LCMScheduler
import torch
from diffusers.utils import load_image

model_id = "sd-dreambooth-library/herge-style"
lcm_lora_id = "latent-consistency/lcm-lora-sdv1-5"

pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)

pipe.load_ip_adapter("h94/IP-Adapter", subfolder="models", weight_name="ip-adapter_sd15.bin")
pipe.load_lora_weights(lcm_lora_id)
pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
pipe.enable_model_cpu_offload()

prompt = "best quality, high quality"
image = load_image("https://user-images.githubusercontent.com/24734142/266492875-2d50d223-8475-44f0-a7c6-08b51cb53572.png")
images = pipe(
prompt=prompt,
ip_adapter_image=image,
num_inference_steps=4,
guidance_scale=1,
).images[0]
''''

This code runs fine, but when I change the load_ip_adapter to 'ip-adapter-plus-face_sd15.bin' or 'ip-adapter-plus_sd15.bin', it gives this error.

image.png

Did I miss something? Please help, thank you so much :D

you should install the latest repo of https://github.com/huggingface/diffusers.git the plus version will be supported in the next version of diffusers.

Install the latest repo works, thank youu

sleepy-chrisy changed discussion status to closed

Sign up or log in to comment