feat(diffusers): add support for wan2.2

[mudler]

Description

This PR adds support to generate videos with wan2.2. This adds support for I2V and T2V models (seems S2V is not in diffusers, yet).

Notes for Reviewers

Tested with:

• WAN 2.1

parameters:
    model: Wan-AI/Wan2.1-T2V-1.3B-Diffusers
name: wan21
f16: true
backend: diffusers
known_usecases:
    - FLAG_VIDEO
diffusers:
    cuda: true
    pipeline_type: WanPipeline
step: 40
options:
    - guidance_scale:5.0
    - num_frames:81
    - torch_dtype:bf16

 curl -X POST http://localhost:8080/video -H "Content-Type: application/json" -H "Authorization: Bearer XXXXX" -d '{
    "model": "wan21",
    "prompt": "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage.",
    "negative_prompt": "Bright tones, overexposed, static",
    "width": 832,
    "height": 480,
    "num_frames": 81,
    "fps": 16,
    "seed": 42,
    "cfg_scale": 5.0,
    "step": 40
  }'

Signed commits

• Yes, I signed my commits.

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	13e8e36
🔍 Latest deploy log	https://app.netlify.com/projects/localai/deploys/68b00d5184f5c000085c4fb8
😎 Deploy Preview	https://deploy-preview-6153--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.