Wan VACE

[a-r-r-o-w]

Checkpoints (temporary; only for the time being until official weights are hosted):

• https://huggingface.co/a-r-r-o-w/Wan-VACE-1.3B-diffusers

T2V

import torch
from diffusers import AutoencoderKLWan, WanVACEPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video

model_id = "/raid/aryan/diffusers-wan-vace-1.3b/"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanVACEPipeline.from_pretrained(model_id, 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.to("cuda")

prompt = "A sleek, humanoid robot stands in a vast warehouse filled with neatly stacked cardboard boxes on industrial shelves. The robot's metallic body gleams under the bright, even lighting, highlighting its futuristic design and intricate joints. A glowing blue light emanates from its chest, adding a touch of advanced technology. The background is dominated by rows of boxes, suggesting a highly organized storage system. The floor is lined with wooden pallets, enhancing the industrial setting. The camera remains static, capturing the robot's poised stance amidst the orderly environment, with a shallow depth of field that keeps the focus on the robot while subtly blurring the background for a cinematic effect."
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"

output = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=480,
    width=832,
    num_frames=81,
    num_inference_steps=30,
    guidance_scale=5.0,
    conditioning_scale=0.0,
    # conditioning_scale=1.0,
    generator=torch.Generator().manual_seed(0),
).frames[0]
export_to_video(output, "output.mp4", fps=16)

`conditioning_scale=0`	`conditioning_scale=1`
output2.mp4	output.mp4

I2V

import torch
import PIL.Image
from diffusers import AutoencoderKLWan, WanVACEPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image


def prepare_video_and_mask(img: PIL.Image.Image, height: int, width: int, num_frames: int):
    img = img.resize((width, height))
    frames = [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 - 1))
    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 - 1)]
    return frames, mask


model_id = "/raid/aryan/diffusers-wan-vace-1.3b/"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanVACEPipeline.from_pretrained(model_id, 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.to("cuda")

prompt = "An astronaut emerging from a cracked, otherworldly egg on the barren surface of the Moon—his form silhouetted against the stark lunar dust, as if being born into silence. The vast darkness of space looms behind, punctuated by distant stars, capturing the immense depth and isolation of the cosmos. The scene is rendered in ultra-realistic, cinematic detail, with dramatic lighting and a breath-taking, movie-like camera angle that evokes awe and mystery—blending themes of rebirth, exploration, and the uncanny."
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"
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg")

height = 480
width = 832
num_frames = 81
video, mask = prepare_video_and_mask(image, 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=30,
    guidance_scale=5.0,
    generator=torch.Generator().manual_seed(42),
).frames[0]
export_to_video(output, "output.mp4", fps=16)

output.mp4

V2LF

import torch
import PIL.Image
from diffusers import AutoencoderKLWan, WanVACEPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image


def prepare_video_and_mask(img: PIL.Image.Image, height: int, width: int, num_frames: int):
    img = img.resize((width, height))
    frames = []
    # 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 - 1))
    frames.append(img)
    mask_black = PIL.Image.new("L", (width, height), 0)
    mask_white = PIL.Image.new("L", (width, height), 255)
    mask = [*[mask_white] * (num_frames - 1), mask_black]
    return frames, mask


model_id = "/raid/aryan/diffusers-wan-vace-1.3b/"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanVACEPipeline.from_pretrained(model_id, 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.to("cuda")

prompt = "An astronaut emerging from a cracked, otherworldly egg on the barren surface of the Moon—his form silhouetted against the stark lunar dust, as if being born into silence. The vast darkness of space looms behind, punctuated by distant stars, capturing the immense depth and isolation of the cosmos. The scene is rendered in ultra-realistic, cinematic detail, with dramatic lighting and a breath-taking, movie-like camera angle that evokes awe and mystery—blending themes of rebirth, exploration, and the uncanny."
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"
image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/astronaut.jpg")

height = 480
width = 832
num_frames = 81
video, mask = prepare_video_and_mask(image, 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=30,
    guidance_scale=5.0,
    generator=torch.Generator().manual_seed(42),
).frames[0]
export_to_video(output, "output.mp4", fps=16)

output.mp4

FLF2V

import torch
import PIL.Image
from diffusers import AutoencoderKLWan, WanVACEPipeline
from diffusers.schedulers.scheduling_unipc_multistep import UniPCMultistepScheduler
from diffusers.utils import export_to_video, load_image


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


model_id = "/raid/aryan/diffusers-wan-vace-1.3b/"
vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
pipe = WanVACEPipeline.from_pretrained(model_id, 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.to("cuda")

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=30,
    guidance_scale=5.0,
    generator=torch.Generator().manual_seed(42),
).frames[0]
export_to_video(output, "output.mp4", fps=16)

output.mp4

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.