Krea realtime video (#1011)

* krea-realtime-video

* Add Krea real-time video inference and training support

* Delete .gitignore

* update README

* update README

---------

Co-authored-by: Artiprocher <wangye87v5@hotmail.com>
Co-authored-by: Jintao Huang <huangjintao.hjt@alibaba-inc.com>
Co-authored-by: Zhongjie Duan <35051019+Artiprocher@users.noreply.github.com>

examples/wanvideo/model_training/full/krea-realtime-video.sh

@@ -0,0 +1,12 @@
+accelerate launch --config_file examples/wanvideo/model_training/full/accelerate_config_14B.yaml examples/wanvideo/model_training/train.py \
+  --dataset_base_path data/example_video_dataset \
+  --dataset_metadata_path data/example_video_dataset/metadata.csv \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "krea/krea-realtime-video:krea-realtime-video-14b.safetensors,Wan-AI/Wan2.1-T2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-T2V-14B:Wan2.1_VAE.pth" \
+  --learning_rate 1e-5 \
+  --num_epochs 2 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/krea-realtime-video_full" \
+  --trainable_models "dit"

examples/wanvideo/model_training/lora/krea-realtime-video.sh

@@ -0,0 +1,14 @@
+accelerate launch examples/wanvideo/model_training/train.py \
+  --dataset_base_path data/example_video_dataset \
+  --dataset_metadata_path data/example_video_dataset/metadata.csv \
+  --height 480 \
+  --width 832 \
+  --dataset_repeat 100 \
+  --model_id_with_origin_paths "krea/krea-realtime-video:krea-realtime-video-14b.safetensors,Wan-AI/Wan2.1-T2V-14B:models_t5_umt5-xxl-enc-bf16.pth,Wan-AI/Wan2.1-T2V-14B:Wan2.1_VAE.pth" \
+  --learning_rate 1e-4 \
+  --num_epochs 5 \
+  --remove_prefix_in_ckpt "pipe.dit." \
+  --output_path "./models/train/krea-realtime-video_lora" \
+  --lora_base_model "dit" \
+  --lora_target_modules "q,k,v,o,ffn.0,ffn.2" \
+  --lora_rank 32

examples/wanvideo/model_training/validate_full/krea-realtime-video.py

@@ -0,0 +1,28 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData, load_state_dict
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="krea/krea-realtime-video", origin_file_pattern="krea-realtime-video-14b.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+state_dict = load_state_dict("models/train/krea-realtime-video_full/epoch-1.safetensors")
+pipe.dit.load_state_dict(state_dict)
+pipe.enable_vram_management()
+
+# Text-to-video
+video = pipe(
+    prompt="a cat sitting on a boat",
+    num_inference_steps=6, num_frames=81,
+    seed=0, tiled=True,
+    cfg_scale=1,
+    sigma_shift=20,
+)
+save_video(video, "output.mp4", fps=15, quality=5)

examples/wanvideo/model_training/validate_lora/krea-realtime-video.py

@@ -0,0 +1,28 @@
+import torch
+from PIL import Image
+from diffsynth import save_video, VideoData, load_state_dict
+from diffsynth.pipelines.wan_video_new import WanVideoPipeline, ModelConfig
+
+
+pipe = WanVideoPipeline.from_pretrained(
+    torch_dtype=torch.bfloat16,
+    device="cuda",
+    model_configs=[
+        ModelConfig(model_id="krea/krea-realtime-video", origin_file_pattern="krea-realtime-video-14b.safetensors", offload_device="cpu"),
+        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth", offload_device="cpu"),
+        ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="Wan2.1_VAE.pth", offload_device="cpu"),
+    ],
+)
+
+pipe.load_lora(pipe.dit, "models/train/krea-realtime-video_lora/epoch-4.safetensors", alpha=1)
+pipe.enable_vram_management()
+
+# Text-to-video
+video = pipe(
+    prompt="a cat sitting on a boat",
+    num_inference_steps=6, num_frames=81,
+    seed=0, tiled=True,
+    cfg_scale=1,
+    sigma_shift=20,
+)
+save_video(video, "output.mp4", fps=15, quality=5)