[new-model] Re-add PAN2 text-to-video and image-to-video (reverts #2025)

This reverts commit 6743f4b4b, restoring #1961.

examples/inference/basic/basic_pan2.py

@@ -0,0 +1,40 @@
+import os
+
+from fastvideo import VideoGenerator
+
+# PAN2 is trained on the structured captions its prompt rewriter produces (serialized as one-line JSON). Plain
+# prompts like this one work, with weaker results.
+PROMPT = ("A red fox trots through fresh snow in a pine forest at dawn, its breath visible in the cold air. "
+          "The camera tracks it from the side at ground level as low golden light filters through the trees.")
+
+OUTPUT_PATH = "video_samples_pan2"
+MODEL_PATH = os.environ.get("PAN2_MODEL_PATH", "IFM/PAN2")
+
+# Set to a first frame (e.g. "assets/images/girl.png") for image-to-video; the same pipeline runs both modes.
+IMAGE_PATH = None
+
+
+def main():
+    # The 29B DiT runs in bf16; with more GPUs, num_gpus enables Ulysses sequence parallelism (the 32 attention
+    # heads must be divisible by it).
+    generator = VideoGenerator.from_pretrained(
+        MODEL_PATH,
+        num_gpus=int(os.environ.get("PAN2_NUM_GPUS", "1")),
+        use_fsdp_inference=False,
+        dit_cpu_offload=False,
+        dit_layerwise_offload=False,
+        vae_cpu_offload=False,
+        text_encoder_cpu_offload=True,
+        pin_cpu_memory=True,
+    )
+
+    generator.generate_video(
+        PROMPT,
+        image_path=IMAGE_PATH,
+        output_path=OUTPUT_PATH,
+        save_video=True,
+    )
+
+
+if __name__ == "__main__":
+    main()

examples/serving/README.md

@@ -90,6 +90,7 @@ uncovered registry families.
 | `openai_hunyuan15_i2v_480p.yaml` | HunyuanVideo 1.5 I2V 480p | image-to-video | 1 |
 | `openai_kandinsky6_ti2va.yaml` | Kandinsky 6 Pro TI2VA | text/image-to-video with audio | 1 |
 | `openai_kandinsky6_ti2va_distilled.yaml` | Kandinsky 6 Pro-distill TI2VA | text/image-to-video with audio | 1 |
+| `openai_pan2.yaml` | PAN 2 | text/image-to-video | 1 |
 | `openai_ltx2_distilled.yaml` | LTX2 Distilled | text-to-video with audio | 4 |
 | `openai_flux1_dev.yaml` | FLUX.1-dev | text-to-image | 1 |
 | `openai_flux2_dev.yaml` | FLUX.2-dev | text-to-image | 1 |

examples/serving/openai_pan2.yaml

@@ -0,0 +1,36 @@
+# OpenAI-compatible server for PAN 2 text-to-video and first-frame image-to-video.
+#   fastvideo serve --config examples/serving/openai_pan2.yaml
+# Omit image_reference for text-to-video; send it (or input_reference) for image-to-video.
+generator:
+  model_path: IFM/PAN2
+  engine:
+    num_gpus: 1
+    use_fsdp_inference: false
+    parallelism:
+      tp_size: 1
+      sp_size: 1
+    offload:
+      dit: false
+      dit_layerwise: false
+      vae: false
+      text_encoder: true
+      pin_cpu_memory: true
+  pipeline:
+    workload_type: t2v
+
+server:
+  host: 0.0.0.0
+  port: 8000
+  output_dir: outputs/openai_pan2
+  served_model_name: pan2
+
+default_request:
+  sampling:
+    height: 704
+    width: 1248
+    num_frames: 313
+    fps: 24
+    num_inference_steps: 50
+    guidance_scale: 3.0
+  output:
+    return_frames: false