Support HunyuanVideo image to video model.

comfy_extras/nodes_hunyuan.py

@@ -1,4 +1,5 @@
 import nodes
+import node_helpers
 import torch
 import comfy.model_management
 
@@ -38,7 +39,73 @@ class EmptyHunyuanLatentVideo:
         latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
         return ({"samples":latent}, )
 
+PROMPT_TEMPLATE_ENCODE_VIDEO_I2V = (
+    "<|start_header_id|>system<|end_header_id|>\n\n<image>\nDescribe the video by detailing the following aspects according to the reference image: "
+    "1. The main content and theme of the video."
+    "2. The color, shape, size, texture, quantity, text, and spatial relationships of the objects."
+    "3. Actions, events, behaviors temporal relationships, physical movement changes of the objects."
+    "4. background environment, light, style and atmosphere."
+    "5. camera angles, movements, and transitions used in the video:<|eot_id|>\n\n"
+    "<|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|>"
+    "<|start_header_id|>assistant<|end_header_id|>\n\n"
+)
+
+class TextEncodeHunyuanVideo_ImageToVideo:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "clip": ("CLIP", ),
+            "clip_vision_output": ("CLIP_VISION_OUTPUT", ),
+            "prompt": ("STRING", {"multiline": True, "dynamicPrompts": True}),
+            }}
+    RETURN_TYPES = ("CONDITIONING",)
+    FUNCTION = "encode"
+
+    CATEGORY = "advanced/conditioning"
+
+    def encode(self, clip, clip_vision_output, prompt):
+        tokens = clip.tokenize(prompt, llama_template=PROMPT_TEMPLATE_ENCODE_VIDEO_I2V, image_embeds=clip_vision_output.mm_projected)
+        return (clip.encode_from_tokens_scheduled(tokens), )
+
+
+class HunyuanImageToVideo:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {"positive": ("CONDITIONING", ),
+                             "vae": ("VAE", ),
+                             "width": ("INT", {"default": 848, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                             "height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                             "length": ("INT", {"default": 53, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),
+                             "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
+                },
+                "optional": {"start_image": ("IMAGE", ),
+                }}
+
+    RETURN_TYPES = ("CONDITIONING", "LATENT")
+    RETURN_NAMES = ("positive", "latent")
+    FUNCTION = "encode"
+
+    CATEGORY = "conditioning/video_models"
+
+    def encode(self, positive, vae, width, height, length, batch_size, start_image=None):
+        latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+        if start_image is not None:
+            start_image = comfy.utils.common_upscale(start_image[:length, :, :, :3].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+
+            concat_latent_image = vae.encode(start_image)
+            mask = torch.ones((1, 1, latent.shape[2], concat_latent_image.shape[-2], concat_latent_image.shape[-1]), device=start_image.device, dtype=start_image.dtype)
+            mask[:, :, :((start_image.shape[0] - 1) // 4) + 1] = 0.0
+
+            positive = node_helpers.conditioning_set_values(positive, {"concat_latent_image": concat_latent_image, "concat_mask": mask})
+
+        out_latent = {}
+        out_latent["samples"] = latent
+        return (positive, out_latent)
+
+
 NODE_CLASS_MAPPINGS = {
     "CLIPTextEncodeHunyuanDiT": CLIPTextEncodeHunyuanDiT,
+    "TextEncodeHunyuanVideo_ImageToVideo": TextEncodeHunyuanVideo_ImageToVideo,
     "EmptyHunyuanLatentVideo": EmptyHunyuanLatentVideo,
+    "HunyuanImageToVideo": HunyuanImageToVideo,
 }