charles2530/Wan2.2-T2V-A14B-Diffusion-AWQ-INT4

Instalación y uso básico con Diffusers:

pip install -U diffusers transformers accelerate

import torch
from diffusers import DiffusionPipeline

# Cambiar a "mps" para dispositivos Apple
pipe = DiffusionPipeline.from_pretrained(
    "charles2530/Wan2.2-T2V-A14B-Diffusion-AWQ-INT4",
    dtype=torch.bfloat16,
    device_map="cuda"
)

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

Ejemplo de inferencia Wan2.2 T2V a 720P sin extensión de prompt:

python generate.py --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --offload_model True --convert_model_dtype --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."

Ejemplo multi-GPU con FSDP y DeepSpeed Ulysses:

torchrun --nproc_per_node=8 generate.py --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."

Uso con Diffusers avanzado:

import torch
import numpy as np
from diffusers import WanPipeline, AutoencoderKLWan
from diffusers.utils import export_to_video, load_image

dtype = torch.bfloat16
device = "cuda:2"

vae = AutoencoderKLWan.from_pretrained(
    "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
    subfolder="vae",
    torch_dtype=torch.float32
)
pipe = WanPipeline.from_pretrained(
    "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
    vae=vae,
    torch_dtype=dtype
)
pipe.to(device)

height = 720
width = 1280
prompt = "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"

output = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    height=height,
    width=width,
    num_frames=81,
    guidance_scale=4.0,
    guidance_scale_2=3.0,
    num_inference_steps=40,
).frames[0]

export_to_video(output, "t2v_out.mp4", fps=16)

Nota: para esta variante de WanPipeline se indica que hacen falta funciones disponibles en la rama principal de Diffusers:

pip install git+https://github.com/huggingface/diffusers