PencilHu commited on
Commit
59b4152
·
verified ·
1 Parent(s): ff8bd5a

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +0 -0
  2. OVERFIT_TROUBLESHOOTING.md +115 -0
  3. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/custom_checkpoint_0.pkl +3 -0
  4. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/model.safetensors +3 -0
  5. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/optimizer.bin +3 -0
  6. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/random_states_0.pkl +3 -0
  7. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/scheduler.bin +3 -0
  8. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/trainer_state.json +1 -0
  9. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/weights.safetensors +3 -0
  10. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/custom_checkpoint_0.pkl +3 -0
  11. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/model.safetensors +3 -0
  12. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/optimizer.bin +3 -0
  13. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/random_states_0.pkl +3 -0
  14. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/scheduler.bin +3 -0
  15. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/trainer_state.json +1 -0
  16. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/weights.safetensors +3 -0
  17. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/custom_checkpoint_0.pkl +3 -0
  18. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/model.safetensors +3 -0
  19. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/optimizer.bin +3 -0
  20. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/random_states_0.pkl +3 -0
  21. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/scheduler.bin +3 -0
  22. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/trainer_state.json +1 -0
  23. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/weights.safetensors +3 -0
  24. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/converted_weights.safetensors +3 -0
  25. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/debug.log +10 -0
  26. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/ref_0/id0_img0.png +3 -0
  27. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/ref_0/id0_img1.png +3 -0
  28. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/ref_0/id0_img2.png +3 -0
  29. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/debug.log +10 -0
  30. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/ref_0/id0_img0.png +3 -0
  31. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/ref_0/id0_img1.png +3 -0
  32. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/ref_0/id0_img2.png +3 -0
  33. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/debug.log +5 -0
  34. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/ref_0/id0_img0.png +3 -0
  35. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/ref_0/id0_img1.png +3 -0
  36. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/ref_0/id0_img2.png +3 -0
  37. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/debug.log +5 -0
  38. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/ref_0/id0_img0.png +3 -0
  39. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/ref_0/id0_img1.png +3 -0
  40. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/ref_0/id0_img2.png +3 -0
  41. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/debug.log +5 -0
  42. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/ref_0/id0_img0.png +3 -0
  43. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/ref_0/id0_img1.png +3 -0
  44. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/ref_0/id0_img2.png +3 -0
  45. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/debug.log +5 -0
  46. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/ref_0/id0_img0.png +3 -0
  47. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/ref_0/id0_img1.png +3 -0
  48. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/ref_0/id0_img2.png +3 -0
  49. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_103/debug.log +5 -0
  50. multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_103/ref_0/id0_img0.png +3 -0
.gitattributes CHANGED
The diff for this file is too large to render. See raw diff
 
OVERFIT_TROUBLESHOOTING.md ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Overfit 排查清单(从数据 → 训练 → 推理)
2
+
3
+ 下面按“最可能导致结果糊”的问题优先级排序。每一条都附带定位方式和建议修复思路。
4
+
5
+ ## 1. 数据与标注是否真的被模型用上
6
+
7
+ ### 1.1 文本 prompt 在训练与推理不一致(高优先级)
8
+ - 现状:
9
+ - 训练时 `pre_shot_caption` 被固定为 `["xxx", "xxx", "xxx"]`
10
+ - 推理时 `overfit_infer_debug.py` 会读取 `dataset.json` 的 `text` 作为 prompt
11
+ - 影响:模型训练时从未见过真实文本,推理时给真实文本会导致条件不匹配,输出容易发散或模糊。
12
+ - 定位:
13
+ - `multi-shot/multi_view/datasets/videodataset.py` 的 `__getitem__` 硬编码 `pre_shot_caption`
14
+ - 建议:
15
+ - 训练时用真实 `text`(或按 shot 拆分后的文本)替换 `pre_shot_caption`
16
+ - 或推理时也用 `"xxx"` 保持一致(不推荐)
17
+
18
+ ### 1.2 overfit 推理只跑了 test split(高优先级)
19
+ - 现状:
20
+ - `overfit_infer_debug.py` 里 `training=False`,Dataset 只使用 `data_test`
21
+ - 你的日志里 `Dataset size: 1`,说明只在 test 上推理
22
+ - 影响:过拟合训练是在 `data_train` 上,推理却在 test 上,必然看不到“过拟合效果”
23
+ - 定位:
24
+ - `MulltiShot_MultiView_Dataset(..., training=False)`
25
+ - 建议:
26
+ - overfit 验证时改为 `training=True` 或直接读取全部数据(不做 train/test split)
27
+
28
+ ### 1.3 每次取随机 5 秒片段(高优先级)
29
+ - 现状:
30
+ - `load_video_crop_ref_image` 每次随机切 5 秒,训练/推理都不确定
31
+ - 影响:同一个 index 每次取到不同片段,过拟合目标不稳定 → 输出糊
32
+ - 建议:
33
+ - overfit 模式下固定切片(比如固定从第 0 帧开始)
34
+ - 或设置固定随机种子,并在推理里复用同一个切片
35
+
36
+ ## 2. 数据预处理是否正确(process_data)
37
+
38
+ ### 2.1 检查处理后的视频尺寸/帧率
39
+ ```bash
40
+ python - <<'PY'
41
+ import json, imageio
42
+ from pathlib import Path
43
+
44
+ path = Path('/data/rczhang/PencilFolder/multi-shot/processed/dataset.json')
45
+ data = json.load(path.open())
46
+ first = next(iter(data.values()))
47
+ video = first['disk_path']
48
+ reader = imageio.get_reader(video)
49
+ meta = reader.get_meta_data()
50
+ frame = reader.get_data(0)
51
+ reader.close()
52
+ print('video:', video)
53
+ print('fps:', meta.get('fps'))
54
+ print('shape:', frame.shape) # 期望 (480, 832, 3)
55
+ PY
56
+ ```
57
+ - 期望:fps=16,shape=(480, 832, 3)
58
+
59
+ ### 2.2 检查 ID 图是否存在、数量够不够
60
+ ```bash
61
+ python - <<'PY'
62
+ import json, os
63
+ from pathlib import Path
64
+
65
+ path = Path('/data/rczhang/PencilFolder/multi-shot/processed/dataset.json')
66
+ data = json.load(path.open())
67
+ first = next(iter(data.values()))
68
+ id_dir = Path(first['id_dir'])
69
+ print('id_dir exists:', id_dir.exists())
70
+ print('id_names:', first.get('id_names'))
71
+ for name in first.get('id_names', []):
72
+ imgs = list((id_dir / name).glob('*'))
73
+ print(name, 'num_imgs:', len(imgs))
74
+ PY
75
+ ```
76
+
77
+ ## 3. 训练配置是否支持“过拟合检查”
78
+
79
+ ### 3.1 训练是否在用 ref_images
80
+ - `train_args.zero_face_ratio`=0.1 会随机把 ref 清空 10% 步。
81
+ - 过拟合排查建议:临时设为 `0.0`,确保 ID 图一直生效。
82
+
83
+ ### 3.2 训练是否从旧 checkpoint 继续
84
+ - `resume_from_checkpoint: True`
85
+ - 如果之前的数据或 prompt 变了,旧 ckpt 会污染。
86
+ - 建议:排查时用新的输出目录或手动关闭 resume。
87
+
88
+ ## 4. 推理配置是否合理
89
+
90
+ ### 4.1 纯 prompt 推理 vs v2v
91
+ - 你现在默认是纯 prompt(`input_video=None`),这是合理的。
92
+ - 如果要确认模型是否“记住”训练样本,可临时开 v2v:
93
+ - `--use_input_video`
94
+ - 这只用于 sanity check,不是最终推理形态。
95
+
96
+ ### 4.2 采样步数过少
97
+ - `num_inference_steps=8` 非常少,容易糊。
98
+ - 排查建议:先用 20~50 步看看清晰度提升。
99
+
100
+ ## 5. 模型与权重是否正确
101
+
102
+ ### 5.1 确认加载的是你训练出的最新 checkpoint
103
+ - `overfit_infer_debug.py` 默认取最新 `checkpoint-step-*`
104
+ - 建议手动指定 `--checkpoint_path` 再确认一次。
105
+
106
+ ### 5.2 只训练了 DiT
107
+ - `trainable_models: dit`,text encoder 和 VAE 都冻结
108
+ - 对于过拟合一般没问题,但如果 prompt 变化很大,text encoder 冻结会让文本条件效果变弱。
109
+
110
+ ## 快速结论(最可能导致“全是糊图”的 3 个点)
111
+ 1) **训练/推理 prompt 不一致(训练固定 "xxx",推理用真实 text)**
112
+ 2) **overfit 推理用的是 test split,不是训练集**
113
+ 3) **每次都随机 5 秒片段,过拟合目标不稳定**
114
+
115
+ 如果你愿意,我可以按这个顺序逐一修掉并验证。
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/custom_checkpoint_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33034d45fdab3d8a29157ff26696c9715757dd8d98a0303bfc0a6cbf096cc3a6
3
+ size 1333
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d80e0d4a0e82af3c59d22a1ab4393c381e2c818eeac07d2dfaab5de636181fb
3
+ size 22770922152
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77932c7804d268d4a5e86fb931239710f7cda353f376c4e5db55f1bc92ff9730
3
+ size 19999867838
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad6e005396b1bd1f9ffbd8b85ff8201c2403424f3b3fe9e1e3d679a689a0ae49
3
+ size 14757
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebd442f8f9275fbbec110e74dd49ce951cd2f879e41aa4af850720f5f1e1ce1
3
+ size 1465
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/trainer_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"global_step": 450}
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-450-epoch-113/weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a342072c8f551c9714b63b9fef4f91c8bf181b7c91378612c1b109c25329ff4
3
+ size 9999659704
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/custom_checkpoint_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16091977b6e9280ab8ccb5c76eb208ad1c0c6a73ea0510dfba8d996c8afdee3f
3
+ size 1333
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390d4dde8feb0a40d2ded2fb1f70da9a8ea266d955664b269be1e55912afe999
3
+ size 22770922152
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5d9be57ee5306984a8da64b49611be3ed94857cda09e2888021b1fcd02f5dc
3
+ size 19999867838
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0b2e9d8d1744a3a9a33c5c5a3cf391884fbbe0ed354d373a3c448e8193fe16
3
+ size 14757
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f6dba1b250c9f1bb90971ef51251e8859c3caaa7acf899c528c3bcc225bf25
3
+ size 1465
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/trainer_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"global_step": 600}
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-600-epoch-150/weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f41f0639f62fbd730cdd57da91a91b488120ad3ec9e304f2ffb400c9408ed68
3
+ size 9999659704
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/custom_checkpoint_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b629bb6ce063826d133bd4e545f8d7d15b8342d89b0e15001901487d4b5ed7e2
3
+ size 1333
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6b18f0a7b1daccb31c4a156a88421b49300c9fe8632b4fc0d2b47089bdfc9b
3
+ size 22770922152
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1103a0cf882fb16b74572f2575d91f14658f96af68c79f41f35b998378b7c45
3
+ size 19999867838
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e231dad9214f4ef95bb8e0955398dcc89a289757330e31697e473c8b2bb784bf
3
+ size 14757
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f0df8db4523b5a804e078196e82594f5b6d138fcb8e21f846e7703ddd2831fc
3
+ size 1465
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/trainer_state.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"global_step": 750}
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/checkpoint-step-750-epoch-188/weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c24186eb803094ae3b5c5952b0f29685953d3f99eaef1f57b5ec4b5a1b17e1
3
+ size 9999659704
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/converted_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d5d43bce868daf997c1069295acd8d9689ff2e09a3482eab2c070e7ec5a968
3
+ size 9999659672
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/debug.log ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ ================================================================================
2
+ [debug_infer] epoch=0 index=0
3
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
4
+ num_frames=81 ref_num=3 ID_num=1
5
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
6
+ ================================================================================
7
+ [debug_infer] epoch=0 index=0
8
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
9
+ num_frames=81 ref_num=3 ID_num=1
10
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/ref_0/id0_img0.png ADDED

Git LFS Details

  • SHA256: 00587aab7656bac9b30772d4bf347f21147eddf5987a7dade394bac608d17447
  • Pointer size: 131 Bytes
  • Size of remote file: 329 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/ref_0/id0_img1.png ADDED

Git LFS Details

  • SHA256: f3532284cc4dac1c88329ff55bb2c47c15e177596313bb73433712436bf36b0d
  • Pointer size: 131 Bytes
  • Size of remote file: 217 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_0/ref_0/id0_img2.png ADDED

Git LFS Details

  • SHA256: e85068f43e6d2ab6799cc4950a8d24ac911cb0844c0360c59f2121bad503dde8
  • Pointer size: 131 Bytes
  • Size of remote file: 263 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/debug.log ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ ================================================================================
2
+ [debug_infer] epoch=1 index=0
3
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
4
+ num_frames=81 ref_num=3 ID_num=1
5
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
6
+ ================================================================================
7
+ [debug_infer] epoch=1 index=0
8
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
9
+ num_frames=81 ref_num=3 ID_num=1
10
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/ref_0/id0_img0.png ADDED

Git LFS Details

  • SHA256: 00587aab7656bac9b30772d4bf347f21147eddf5987a7dade394bac608d17447
  • Pointer size: 131 Bytes
  • Size of remote file: 329 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/ref_0/id0_img1.png ADDED

Git LFS Details

  • SHA256: e85068f43e6d2ab6799cc4950a8d24ac911cb0844c0360c59f2121bad503dde8
  • Pointer size: 131 Bytes
  • Size of remote file: 263 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_1/ref_0/id0_img2.png ADDED

Git LFS Details

  • SHA256: f3532284cc4dac1c88329ff55bb2c47c15e177596313bb73433712436bf36b0d
  • Pointer size: 131 Bytes
  • Size of remote file: 217 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/debug.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ================================================================================
2
+ [debug_infer] epoch=10 index=0
3
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
4
+ num_frames=81 ref_num=3 ID_num=1
5
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/ref_0/id0_img0.png ADDED

Git LFS Details

  • SHA256: f3532284cc4dac1c88329ff55bb2c47c15e177596313bb73433712436bf36b0d
  • Pointer size: 131 Bytes
  • Size of remote file: 217 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/ref_0/id0_img1.png ADDED

Git LFS Details

  • SHA256: e85068f43e6d2ab6799cc4950a8d24ac911cb0844c0360c59f2121bad503dde8
  • Pointer size: 131 Bytes
  • Size of remote file: 263 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_10/ref_0/id0_img2.png ADDED

Git LFS Details

  • SHA256: 00587aab7656bac9b30772d4bf347f21147eddf5987a7dade394bac608d17447
  • Pointer size: 131 Bytes
  • Size of remote file: 329 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/debug.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ================================================================================
2
+ [debug_infer] epoch=100 index=0
3
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
4
+ num_frames=81 ref_num=3 ID_num=1
5
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/ref_0/id0_img0.png ADDED

Git LFS Details

  • SHA256: 00587aab7656bac9b30772d4bf347f21147eddf5987a7dade394bac608d17447
  • Pointer size: 131 Bytes
  • Size of remote file: 329 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/ref_0/id0_img1.png ADDED

Git LFS Details

  • SHA256: e85068f43e6d2ab6799cc4950a8d24ac911cb0844c0360c59f2121bad503dde8
  • Pointer size: 131 Bytes
  • Size of remote file: 263 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_100/ref_0/id0_img2.png ADDED

Git LFS Details

  • SHA256: f3532284cc4dac1c88329ff55bb2c47c15e177596313bb73433712436bf36b0d
  • Pointer size: 131 Bytes
  • Size of remote file: 217 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/debug.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ================================================================================
2
+ [debug_infer] epoch=101 index=0
3
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
4
+ num_frames=81 ref_num=3 ID_num=1
5
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/ref_0/id0_img0.png ADDED

Git LFS Details

  • SHA256: 00587aab7656bac9b30772d4bf347f21147eddf5987a7dade394bac608d17447
  • Pointer size: 131 Bytes
  • Size of remote file: 329 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/ref_0/id0_img1.png ADDED

Git LFS Details

  • SHA256: e85068f43e6d2ab6799cc4950a8d24ac911cb0844c0360c59f2121bad503dde8
  • Pointer size: 131 Bytes
  • Size of remote file: 263 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_101/ref_0/id0_img2.png ADDED

Git LFS Details

  • SHA256: f3532284cc4dac1c88329ff55bb2c47c15e177596313bb73433712436bf36b0d
  • Pointer size: 131 Bytes
  • Size of remote file: 217 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/debug.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ================================================================================
2
+ [debug_infer] epoch=102 index=0
3
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
4
+ num_frames=81 ref_num=3 ID_num=1
5
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/ref_0/id0_img0.png ADDED

Git LFS Details

  • SHA256: 00587aab7656bac9b30772d4bf347f21147eddf5987a7dade394bac608d17447
  • Pointer size: 131 Bytes
  • Size of remote file: 329 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/ref_0/id0_img1.png ADDED

Git LFS Details

  • SHA256: f3532284cc4dac1c88329ff55bb2c47c15e177596313bb73433712436bf36b0d
  • Pointer size: 131 Bytes
  • Size of remote file: 217 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_102/ref_0/id0_img2.png ADDED

Git LFS Details

  • SHA256: e85068f43e6d2ab6799cc4950a8d24ac911cb0844c0360c59f2121bad503dde8
  • Pointer size: 131 Bytes
  • Size of remote file: 263 kB
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_103/debug.log ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ================================================================================
2
+ [debug_infer] epoch=103 index=0
3
+ video_path=/data/rczhang/PencilFolder/multi-shot/processed/Data1/2.mp4
4
+ num_frames=81 ref_num=3 ID_num=1
5
+ prompt=['画面右侧的黄种人中年男性,穿着深色西装外套和白色衬衫,面朝镜头坐在沙发上,身体前倾,目光看向画面左侧的人,随后微微低头,又抬头看向画面左侧的人。画面左侧的人背对镜头,只露出部分头部和肩膀,穿着蓝色衣服,背景中可以看到木质墙面装饰,墙上挂有带有几何图案的装饰画,增添了空间的艺术感。透过窗户,自然光线洒入室内,营造出明亮而温馨的氛围。视频以晃动的运镜手法,在特写上半身的镜头下展示。', '画面中间的黄种人中年男性面向画面左侧,目光专注地注视着前方。他的头部微微晃动。他穿着深色西装和白色衬衫,头发整齐地向后梳。背景是一面浅色墙壁和一扇带有百叶窗的窗户。整个场景光线柔和,营造出一种安静而专业的氛围。该视频以左摇的运镜手法,在特写胸部以上的画面下拍摄']
multi_view/ckpts/Wan2.2_5B-Multi_view-normal_rope_480_832-3ref_local/debug_infer/epoch_103/ref_0/id0_img0.png ADDED

Git LFS Details

  • SHA256: 00587aab7656bac9b30772d4bf347f21147eddf5987a7dade394bac608d17447
  • Pointer size: 131 Bytes
  • Size of remote file: 329 kB