[refactor]: move examples to generate(request) and from_config

Every example calls VideoGenerator.generate with a nested request instead
of generate_video keywords, and passes settings outside the from_pretrained
convenience keywords through VideoGenerator.from_config at their typed
paths. Each request and generator config equals what the keyword call built.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012M91wnVFmPEvJ9h39r5BH7

examples/inference/optimizations/text_encoder_quant_example.py

@@ -10,26 +10,38 @@ def main(text_encoder_path: str):
     # If a local path is provided, FastVideo will make a best effort
     # attempt to identify the optimal arguments.
     model_name = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
-    generator = VideoGenerator.from_pretrained(
-        model_name,
-        # FastVideo will automatically handle distributed setup
-        num_gpus=1,
-        use_fsdp_inference=True,
-        dit_cpu_offload=True,
-        vae_cpu_offload=False,
-        text_encoder_cpu_offload=False,
-        # AbsMaxFP8 is the quantization method used by ComfyUI;
-        # check fastvideo/layers/quantization/* for more quantization methods
-        override_text_encoder_quant="AbsMaxFP8",
-        # for Wan 2.2, this is the path to "umt5_xxl_fp8_e4m3fn_scaled.safetensors"
-        override_text_encoder_safetensors=text_encoder_path,
-        pin_cpu_memory=True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
-    )
+    generator = VideoGenerator.from_config({
+        "model_path": model_name,
+        "engine": {
+            # FastVideo will automatically handle distributed setup
+            "num_gpus": 1,
+            "use_fsdp_inference": True,
+            "offload": {
+                "dit": True,
+                "vae": False,
+                "text_encoder": False,
+                "pin_cpu_memory": True,  # set to false if low CPU RAM or hit obscure "CUDA error: Invalid argument"
+            },
+            # AbsMaxFP8 is the quantization method used by ComfyUI;
+            # check fastvideo/layers/quantization/* for more quantization methods
+            "quantization": {"text_encoder_quant": "AbsMaxFP8"},
+        },
+        "pipeline": {
+            "components": {
+                # for Wan 2.2, this is the path to "umt5_xxl_fp8_e4m3fn_scaled.safetensors"
+                "text_encoder_weights": text_encoder_path,
+            },
+        },
+    })
 
     # I2V is triggered just by passing in an image_path argument
     prompt = "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline's intricate details and the refreshing atmosphere of the seaside."
     image_path = "https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/wan_i2v_input.JPG"
-    video = generator.generate_video(prompt, output_path=OUTPUT_PATH, save_video=True, image_path=image_path)
+    video = generator.generate({
+        "prompt": prompt,
+        "inputs": {"image_path": image_path},
+        "output": {"output_path": OUTPUT_PATH, "save_video": True},
+    })
 
 
 if __name__ == "__main__":