Merge pull request #436 from mi804/hunyuanvideo_i2v

support hunyuanvideo-i2v

examples/HunyuanVideo/README.md

@@ -8,6 +8,12 @@
 |24G|[hunyuanvideo_24G.py](hunyuanvideo_24G.py)|129|720*1280|The video is consistent with the original implementation, but it requires 5%~10% more time than [hunyuanvideo_80G.py](hunyuanvideo_80G.py)|
 |6G|[hunyuanvideo_6G.py](hunyuanvideo_6G.py)|129|512*384|The base model doesn't support low resolutions. We recommend users to use some LoRA ([example](https://civitai.com/models/1032126/walking-animation-hunyuan-video)) trained using low resolutions.|
 
+[HunyuanVideo-I2V](https://github.com/Tencent/HunyuanVideo-I2V) is the image-to-video generation version of HunyuanVideo. We also provide advanced VRAM management for this model.
+|VRAM required|Example script|Frames|Resolution|Note|
+|-|-|-|-|-|
+|80G|[hunyuanvideo_i2v_80G.py](hunyuanvideo_i2v_80G.py)|129|720p|No VRAM management.|
+|24G|[hunyuanvideo_i2v_24G.py](hunyuanvideo_i2v_24G.py)|129|720p|The video is consistent with the original implementation, but it requires 5%~10% more time than [hunyuanvideo_80G.py](hunyuanvideo_80G.py)|
+
 ## Gallery
 
 Video generated by [hunyuanvideo_80G.py](hunyuanvideo_80G.py) and [hunyuanvideo_24G.py](hunyuanvideo_24G.py):
@@ -21,3 +27,7 @@ https://github.com/user-attachments/assets/2997f107-d02d-4ecb-89bb-5ce1a7f93817
 Video to video generated by [hunyuanvideo_v2v_6G.py](./hunyuanvideo_v2v_6G.py) using [this LoRA](https://civitai.com/models/1032126/walking-animation-hunyuan-video):
 
 https://github.com/user-attachments/assets/4b89e52e-ce42-434e-aa57-08f09dfa2b10
+
+Video generated by [hunyuanvideo_i2v_80G.py](hunyuanvideo_i2v_80G.py) and [hunyuanvideo_i2v_24G.py](hunyuanvideo_i2v_24G.py):
+
+https://github.com/user-attachments/assets/494f252a-c9af-440d-84ba-a8ddcdcc538a

examples/HunyuanVideo/hunyuanvideo_i2v_24G.py

@@ -0,0 +1,43 @@
+import torch
+from diffsynth import ModelManager, HunyuanVideoPipeline, download_models, save_video
+from modelscope import dataset_snapshot_download
+from PIL import Image
+
+
+download_models(["HunyuanVideoI2V"])
+model_manager = ModelManager()
+
+# The DiT model is loaded in bfloat16.
+model_manager.load_models(
+    [
+        "models/HunyuanVideoI2V/transformers/mp_rank_00_model_states.pt"
+    ],
+    torch_dtype=torch.bfloat16,
+    device="cpu"
+)
+
+# The other modules are loaded in float16.
+model_manager.load_models(
+    [
+        "models/HunyuanVideoI2V/text_encoder/model.safetensors",
+        "models/HunyuanVideoI2V/text_encoder_2",
+        'models/HunyuanVideoI2V/vae/pytorch_model.pt'
+    ],
+    torch_dtype=torch.float16,
+    device="cpu"
+)
+# The computation device is "cuda".
+pipe = HunyuanVideoPipeline.from_model_manager(model_manager,
+                                               torch_dtype=torch.bfloat16,
+                                               device="cuda",
+                                               enable_vram_management=True)
+
+dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth",
+                          local_dir="./",
+                          allow_file_pattern=f"data/examples/hunyuanvideo/*")
+
+i2v_resolution = "720p"
+prompt = "An Asian man with short hair in black tactical uniform and white clothes waves a firework stick."
+images = [Image.open("data/examples/hunyuanvideo/0.jpg").convert('RGB')]
+video = pipe(prompt, input_images=images, num_inference_steps=50, seed=0, i2v_resolution=i2v_resolution)
+save_video(video, f"video_{i2v_resolution}_low_vram.mp4", fps=30, quality=6)

examples/HunyuanVideo/hunyuanvideo_i2v_80G.py

@@ -0,0 +1,45 @@
+import torch
+from diffsynth import ModelManager, HunyuanVideoPipeline, download_models, save_video
+from modelscope import dataset_snapshot_download
+from PIL import Image
+
+
+download_models(["HunyuanVideoI2V"])
+model_manager = ModelManager()
+
+# The DiT model is loaded in bfloat16.
+model_manager.load_models(
+    [
+        "models/HunyuanVideoI2V/transformers/mp_rank_00_model_states.pt"
+    ],
+    torch_dtype=torch.bfloat16,
+    device="cuda"
+)
+
+# The other modules are loaded in float16.
+model_manager.load_models(
+    [
+        "models/HunyuanVideoI2V/text_encoder/model.safetensors",
+        "models/HunyuanVideoI2V/text_encoder_2",
+        'models/HunyuanVideoI2V/vae/pytorch_model.pt'
+    ],
+    torch_dtype=torch.float16,
+    device="cuda"
+)
+# The computation device is "cuda".
+pipe = HunyuanVideoPipeline.from_model_manager(model_manager,
+                                               torch_dtype=torch.bfloat16,
+                                               device="cuda",
+                                               enable_vram_management=False)
+# Although you have enough VRAM, we still recommend you to enable offload.
+pipe.enable_cpu_offload()
+
+dataset_snapshot_download(dataset_id="DiffSynth-Studio/examples_in_diffsynth",
+                          local_dir="./",
+                          allow_file_pattern=f"data/examples/hunyuanvideo/*")
+
+i2v_resolution = "720p"
+prompt = "An Asian man with short hair in black tactical uniform and white clothes waves a firework stick."
+images = [Image.open("data/examples/hunyuanvideo/0.jpg").convert('RGB')]
+video = pipe(prompt, input_images=images, num_inference_steps=50, seed=0, i2v_resolution=i2v_resolution)
+save_video(video, f"video_{i2v_resolution}.mp4", fps=30, quality=6)