Fastwan 14B and inp sampling param and optional image_path

fastvideo/configs/pipelines/registry.py

@@ -26,6 +26,7 @@ PIPE_NAME_TO_CONFIG: dict[str, type[PipelineConfig]] = {
     "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers": WanI2V720PConfig,
     "Wan-AI/Wan2.1-T2V-14B-Diffusers": WanT2V720PConfig,
     "FastVideo/FastWan2.1-T2V-1.3B-Diffusers": FastWanT2V480PConfig,
+    "FastVideo/FastWan2.1-T2V-14B-480P-Diffusers": FastWanT2V480PConfig,
     "FastVideo/stepvideo-t2v-diffusers": StepVideoT2VConfig,
     "FastVideo/Wan2.1-VSA-T2V-14B-720P-Diffusers": WanT2V720PConfig,
     # Add other specific weight variants

fastvideo/configs/sample/registry.py

@@ -10,7 +10,8 @@ from fastvideo.configs.sample.wan import (FastWanT2V480PConfig,
                                           WanI2V_14B_480P_SamplingParam,
                                           WanI2V_14B_720P_SamplingParam,
                                           WanT2V_1_3B_SamplingParam,
-                                          WanT2V_14B_SamplingParam)
+                                          WanT2V_14B_SamplingParam,
+                                          Wan2_1_Fun_1_3B_InP_SamplingParam)
 from fastvideo.logger import init_logger
 from fastvideo.utils import (maybe_download_model_index,
                              verify_model_config_and_directory)
@@ -24,8 +25,10 @@ SAMPLING_PARAM_REGISTRY: dict[str, Any] = {
     "Wan-AI/Wan2.1-T2V-14B-Diffusers": WanT2V_14B_SamplingParam,
     "Wan-AI/Wan2.1-I2V-14B-480P-Diffusers": WanI2V_14B_480P_SamplingParam,
     "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers": WanI2V_14B_720P_SamplingParam,
+    "weizhou03/Wan2.1-Fun-1.3B-InP-Diffusers": Wan2_1_Fun_1_3B_InP_SamplingParam,
     "FastVideo/stepvideo-t2v-diffusers": StepVideoT2VSamplingParam,
-    "FastVideo/FastWan2.1-T2V-1.3B-Diffusers": FastWanT2V480PConfig,
+    "FastVideo/FastWan2.1-T2V-1.3B-Diffusers": Wan2_1_Fun_1_3B_InP_SamplingParam,
+    "FastVideo/FastWan2.1-T2V-14B-480P-Diffusers": Wan2_1_Fun_1_3B_InP_SamplingParam,
     # Add other specific weight variants
 }
 

fastvideo/configs/sample/wan.py

@@ -105,3 +105,18 @@ class FastWanT2V480PConfig(WanT2V_1_3B_SamplingParam):
     height: int = 448
     width: int = 832
     fps: int = 16
+
+
+# =============================================
+# ============= Wan2.1 Fun Models =============
+# =============================================
+@dataclass
+class Wan2_1_Fun_1_3B_InP_SamplingParam(SamplingParam):
+    """Sampling parameters for Wan2.1 Fun 1.3B InP model."""
+    height: int = 480
+    width: int = 832
+    num_frames: int = 81
+    fps: int = 16
+    negative_prompt: str | None = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
+    guidance_scale: float = 6.0
+    num_inference_steps: int = 50

fastvideo/pipelines/stages/encoding.py

@@ -48,14 +48,14 @@ class EncodingStage(PipelineStage):
         Returns:
             The batch with encoded outputs.
         """
+        if batch.pil_image is None:
+            return batch
+
         self.vae = self.vae.to(get_local_torch_device())
 
-        assert batch.height is not None
-        assert batch.width is not None
         latent_height = batch.height // self.vae.spatial_compression_ratio
         latent_width = batch.width // self.vae.spatial_compression_ratio
 
-        assert batch.pil_image is not None
         image = batch.pil_image
         image = self.preprocess(
             image,
@@ -194,6 +194,6 @@ class EncodingStage(PipelineStage):
                       fastvideo_args: FastVideoArgs) -> VerificationResult:
         """Verify encoding stage outputs."""
         result = VerificationResult()
-        result.add_check("image_latent", batch.image_latent,
-                         [V.is_tensor, V.with_dims(5)])
+        # result.add_check("image_latent", batch.image_latent,
+        #                  [V.is_tensor, V.with_dims(5)])
         return result

fastvideo/pipelines/stages/image_encoding.py

@@ -55,6 +55,9 @@ class ImageEncodingStage(PipelineStage):
         Returns:
             The batch with encoded prompt embeddings.
         """
+        if batch.pil_image is None:
+            return batch
+
         self.image_encoder = self.image_encoder.to(get_local_torch_device())
 
         image = batch.pil_image
@@ -76,7 +79,7 @@ class ImageEncodingStage(PipelineStage):
                      fastvideo_args: FastVideoArgs) -> VerificationResult:
         """Verify image encoding stage inputs."""
         result = VerificationResult()
-        result.add_check("pil_image", batch.pil_image, V.not_none)
+        # result.add_check("pil_image", batch.pil_image, V.not_none)
         result.add_check("image_embeds", batch.image_embeds, V.is_list)
         return result
 
@@ -84,6 +87,6 @@ class ImageEncodingStage(PipelineStage):
                       fastvideo_args: FastVideoArgs) -> VerificationResult:
         """Verify image encoding stage outputs."""
         result = VerificationResult()
-        result.add_check("image_embeds", batch.image_embeds,
-                         V.list_of_tensors_dims(3))
+        # result.add_check("image_embeds", batch.image_embeds,
+        #                  V.list_of_tensors_dims(3))
         return result