fix: Detect Wan 2.2 I2V base model correctly for image-to-video models

Before this fix, using Wan 2.2 I2V models like 'wan2_2_i2v_a14b' would
incorrectly try to load 'Wan-AI/Wan2.1-T2V-14B-Diffusers' as the base
model because the fallback logic only matched 'wan' generically.

Now the base_model_fallbacks dictionary includes specific entries for:
- Wan 2.2 I2V models: wan2_2_i2v, wan2.2_i2v
- Wan 2.2 T2V models: wan2_2, wan2.2
- Wan 2.1 I2V models: wan2_1_i2v, wan2.1_i2v
- Wan 2.1 T2V models: wan2_1, wan2.1
- Generic Wan fallback: wan

The more specific keys are checked first, so model IDs like
'wan2_2_i2v_a14b' will correctly match 'wan2_2_i2v' and use
'Wan-AI/Wan2.2-I2V-14B-Diffusers' as the base model.

videogen.py

@@ -9199,6 +9199,17 @@ def main(args):
                         base_model_fallbacks = {
                             "ltx": "Lightricks/LTX-Video",
                             "ltxvideo": "Lightricks/LTX-Video",
+                            # Wan 2.2 I2V models
+                            "wan2_2_i2v": "Wan-AI/Wan2.2-I2V-14B-Diffusers",
+                            "wan2.2_i2v": "Wan-AI/Wan2.2-I2V-14B-Diffusers",
+                            "wan2_2": "Wan-AI/Wan2.2-T2V-14B-Diffusers",
+                            "wan2.2": "Wan-AI/Wan2.2-T2V-14B-Diffusers",
+                            # Wan 2.1 models
+                            "wan2_1_i2v": "Wan-AI/Wan2.1-I2V-14B-Diffusers",
+                            "wan2.1_i2v": "Wan-AI/Wan2.1-I2V-14B-Diffusers",
+                            "wan2_1": "Wan-AI/Wan2.1-T2V-14B-Diffusers",
+                            "wan2.1": "Wan-AI/Wan2.1-T2V-14B-Diffusers",
+                            # Generic Wan fallback
                             "wan": "Wan-AI/Wan2.1-T2V-14B-Diffusers",
                             "svd": "stabilityai/stable-video-diffusion-img2vid-xt-1-1",
                             "cogvideo": "THUDM/CogVideoX-5b",