CausVid LoRA key error when loading with diffusers #11709
Description
Describe the bug
when use this lora with vace-diffusers. There will be a key loading error problem
Reproduction
import torch
import PIL.Image
from diffusers import AutoencoderKLWan, WanVACEPipeline, GGUFQuantizationConfig, AutoModel, WanTransformer3DModel
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image
from transformers import UMT5EncoderModel
vae = AutoencoderKLWan.from_pretrained(
"Wan-AI/Wan2.1-VACE-14B-diffusers",
subfolder="vae",
torch_dtype=torch.float32,
)
pipe = WanVACEPipeline.from_pretrained(
"Wan-AI/Wan2.1-VACE-14B-diffusers",
vae=vae,
torch_dtype=torch.bfloat16
)
flow_shift = 5.0 # 5.0 for 720P, 3.0 for 480P
pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config, flow_shift=flow_shift)
pipe.load_lora_weights(
"../mymodels",
weight_name="Wan21_CausVid_14B_T2V_lora_rank32_v2.safetensors",
adapter_name="wan_lora"
)
pipe.set_adapters("wan_lora", "0.53")
pipe.enable_sequential_cpu_offload()
def prepare_video_and_mask(first_img: PIL.Image.Image, last_img: PIL.Image.Image, height: int, width: int, num_frames: int):
first_img = first_img.resize((width, height))
last_img = last_img.resize((width, height))
frames = []
frames.append(first_img)
# Ideally, this should be 127.5 to match original code, but they perform computation on numpy arrays
# whereas we are passing PIL images. If you choose to pass numpy arrays, you can set it to 127.5 to
# match the original code.
frames.extend([PIL.Image.new("RGB", (width, height), (128, 128, 128))] * (num_frames - 2))
frames.append(last_img)
mask_black = PIL.Image.new("L", (width, height), 0)
mask_white = PIL.Image.new("L", (width, height), 255)
mask = [mask_black, *[mask_white] * (num_frames - 2), mask_black]
return frames, mask
prompt = "CG animation style, a small blue bird takes off from the ground, flapping its wings. The bird's feathers are delicate, with a unique pattern on its chest. The background shows a blue sky with white clouds under bright sunshine. The camera follows the bird upward, capturing its flight and the vastness of the sky from a close-up, low-angle perspective."
negative_prompt = "Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards"
first_frame = load_image(
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_first_frame.png"
)
last_frame = load_image(
"https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/flf2v_input_last_frame.png"
)
height = 512
width = 512
num_frames = 81
video, mask = prepare_video_and_mask(first_frame, last_frame, height, width, num_frames)
output = pipe(
video=video,
mask=mask,
prompt=prompt,
negative_prompt=negative_prompt,
height=height,
width=width,
num_frames=num_frames,
num_inference_steps=6,
guidance_scale=1.0,
generator=torch.Generator().manual_seed(42),
).frames[0]
export_to_video(output, "output.mp4", fps=16)Logs
state_dict = _convert_non_diffusers_wan_lora_to_diffusers(state_dict)
File "/data3/anaconda3/envs/photomaker/lib/python3.10/site-packages/diffusers/loaders/lora_conversion_utils.py", line 1619, in _convert_non_diffusers_wan_lora_to_diffusers
converted_state_dict[f"blocks.{i}.attn1.{c}.lora_A.weight"] = original_state_dict.pop(
KeyError: 'blocks.0.self_attn.q.lora_down.weight'System Info
diffusers=0.34.1，python=3.10，ubuntu22.04
Who can help?
No response