[refactor]: migrate examples/scripts to typed VideoGenerator API; rename api/compat.py to api/translation.py

Move all examples/inference and scripts off the legacy
VideoGenerator.from_pretrained(model, **kwargs) +
generate_video(prompt, **kwargs) surface onto the typed
from_config(GeneratorConfig(...)) + generate(GenerationRequest(...))
convention, including the Kandinsky-5 and DreamX-World examples added
on main after the original migration. git-mv api/compat.py to
api/translation.py ('compat' implied a temporary shim; the forward
translation is its honest permanent role) and repoint all importers,
tests, and doc links.

examples/inference/basic/basic_matrixgame2.py

@@ -1,4 +1,6 @@
 from fastvideo import VideoGenerator
+from fastvideo.api import (EngineConfig, GenerationRequest, GeneratorConfig, InputConfig, OffloadConfig, OutputConfig,
+                           SamplingConfig)
 from fastvideo.models.dits.matrixgame2.utils import create_action_presets
 
 import torch
@@ -38,35 +40,48 @@ def main():
     # attempt to identify the optimal arguments.
     config = VARIANT_CONFIG[MODEL_VARIANT]
 
-    generator = VideoGenerator.from_pretrained(
-        config["model_path"],
-        # FastVideo will automatically handle distributed setup
-        num_gpus=1,
-        use_fsdp_inference=False, # set to True if GPU is out of memory
-        dit_cpu_offload=True, # DiT need to be offloaded for MoE
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=True,
-        # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
-        pin_cpu_memory=True,
-        # image_encoder_cpu_offload=False,
+    generator = VideoGenerator.from_config(
+        GeneratorConfig(
+            model_path=config["model_path"],
+            # FastVideo will automatically handle distributed setup
+            engine=EngineConfig(
+                num_gpus=1,
+                use_fsdp_inference=False,  # set to True if GPU is out of memory
+                offload=OffloadConfig(
+                    dit=True,  # DiT need to be offloaded for MoE
+                    vae=False,
+                    text_encoder=True,
+                    # Set pin_cpu_memory to false if CPU RAM is limited and there're no frequent CPU-GPU transfer
+                    pin_cpu_memory=True,
+                ),
+            ),
+        )
     )
 
     num_frames = 597
     actions = create_action_presets(num_frames, keyboard_dim=config["keyboard_dim"])
     grid_sizes = torch.tensor([150, 44, 80])
 
-    generator.generate_video(
-        prompt="",
-        image_path=config["image_url"],
-        mouse_cond=actions["mouse"].unsqueeze(0),
-        keyboard_cond=actions["keyboard"].unsqueeze(0),
-        grid_sizes=grid_sizes,
-        num_frames=num_frames,
-        height=352,
-        width=640,
-        num_inference_steps=50,
-        output_path=OUTPUT_PATH,
-        save_video=True,
+    generator.generate(
+        GenerationRequest(
+            prompt="",
+            inputs=InputConfig(
+                image_path=config["image_url"],
+                mouse_cond=actions["mouse"].unsqueeze(0),
+                keyboard_cond=actions["keyboard"].unsqueeze(0),
+                grid_sizes=grid_sizes,
+            ),
+            sampling=SamplingConfig(
+                num_frames=num_frames,
+                height=352,
+                width=640,
+                num_inference_steps=50,
+            ),
+            output=OutputConfig(
+                output_path=OUTPUT_PATH,
+                save_video=True,
+            ),
+        )
     )