WitneyWW commited on
Commit
826eb44
·
verified ·
1 Parent(s): 1895622

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,15 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ videos/test_add_generated.mp4 filter=lfs diff=lfs merge=lfs -text
37
+ videos/test_add_source.mp4 filter=lfs diff=lfs merge=lfs -text
38
+ videos/test_add_target.mp4 filter=lfs diff=lfs merge=lfs -text
39
+ videos/test_remove_generated.mp4 filter=lfs diff=lfs merge=lfs -text
40
+ videos/test_remove_source.mp4 filter=lfs diff=lfs merge=lfs -text
41
+ videos/test_remove_target.mp4 filter=lfs diff=lfs merge=lfs -text
42
+ videos/train_add_generated.mp4 filter=lfs diff=lfs merge=lfs -text
43
+ videos/train_add_source.mp4 filter=lfs diff=lfs merge=lfs -text
44
+ videos/train_add_target.mp4 filter=lfs diff=lfs merge=lfs -text
45
+ videos/train_remove_generated.mp4 filter=lfs diff=lfs merge=lfs -text
46
+ videos/train_remove_source.mp4 filter=lfs diff=lfs merge=lfs -text
47
+ videos/train_remove_target.mp4 filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,10 +1,15 @@
1
  ---
2
- title: Javisdit Edit Text Both
3
- emoji: 😻
4
- colorFrom: purple
5
- colorTo: gray
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
1
  ---
2
+ title: JavisDiT Edit Inference (text_both_0721)
3
+ emoji: 🎬
4
+ colorFrom: indigo
5
+ colorTo: purple
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
+ # JavisDiT Edit audio-visual object addition & removal
11
+
12
+ Inference samples from the `text_both_0721` checkpoint (epoch001-global_step13000, EMA):
13
+ one test-set and one train-set (overfit check) sample, each run in the **add** and
14
+ **remove** direction, with the target's first frame prepended as the anchor.
15
+ Source / Generated / Target shown side by side, all with audio.
index.html CHANGED
@@ -1,19 +1,106 @@
1
- <!doctype html>
2
- <html>
3
- <head>
4
- <meta charset="utf-8" />
5
- <meta name="viewport" content="width=device-width" />
6
- <title>My static Space</title>
7
- <link rel="stylesheet" href="style.css" />
8
- </head>
9
- <body>
10
- <div class="card">
11
- <h1>Welcome to your static Space!</h1>
12
- <p>You can modify this app directly by editing <i>index.html</i> in the Files and versions tab.</p>
13
- <p>
14
- Also don't forget to check the
15
- <a href="https://huggingface.co/docs/hub/spaces" target="_blank">Spaces documentation</a>.
16
- </p>
17
- </div>
18
- </body>
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  </html>
 
1
+ <!DOCTYPE html>
2
+ <html lang="en">
3
+ <head>
4
+ <meta charset="utf-8">
5
+ <meta name="viewport" content="width=device-width, initial-scale=1">
6
+ <title>JavisDiT Edit — text_both_0721 @ step 13k</title>
7
+ <style>
8
+ :root {
9
+ --bg: #0f1117; --card: #181b24; --border: #2a2f3d;
10
+ --text: #e8eaf0; --muted: #9aa1b5; --accent: #7aa2ff;
11
+ }
12
+ * { box-sizing: border-box; margin: 0; padding: 0; }
13
+ body {
14
+ background: var(--bg); color: var(--text);
15
+ font: 15px/1.55 -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
16
+ padding: 2rem 1.25rem 4rem;
17
+ }
18
+ .wrap { max-width: 1100px; margin: 0 auto; }
19
+ h1 { font-size: 1.5rem; margin-bottom: .35rem; }
20
+ .sub { color: var(--muted); font-size: .92rem; margin-bottom: 2rem; }
21
+ .sub code { color: var(--accent); background: var(--card); padding: .1em .35em; border-radius: 4px; }
22
+ section { margin-bottom: 2.5rem; }
23
+ .sec-head { display: flex; align-items: baseline; gap: .75rem; flex-wrap: wrap; margin-bottom: .9rem; }
24
+ .sec-head h2 { font-size: 1.12rem; }
25
+ .badge {
26
+ font-size: .74rem; font-weight: 600; letter-spacing: .04em; text-transform: uppercase;
27
+ padding: .18em .6em; border-radius: 99px; border: 1px solid var(--border);
28
+ }
29
+ .badge.test { color: #8fd3a7; border-color: #2e5d41; background: #16281d; }
30
+ .badge.train { color: #f0b86a; border-color: #6b5228; background: #2a2113; }
31
+ .prompt { color: var(--muted); font-size: .9rem; }
32
+ .prompt code { color: var(--text); }
33
+ .row { display: grid; grid-template-columns: repeat(3, 1fr); gap: 1rem; }
34
+ @media (max-width: 760px) { .row { grid-template-columns: 1fr; } }
35
+ .cell { background: var(--card); border: 1px solid var(--border); border-radius: 10px; padding: .75rem; }
36
+ .cell.gen { border-color: #3d517e; }
37
+ .cell h3 { font-size: .85rem; font-weight: 600; color: var(--muted); margin-bottom: .55rem; }
38
+ .cell.gen h3 { color: var(--accent); }
39
+ video { width: 100%; border-radius: 6px; display: block; background: #000; }
40
+ .note { color: var(--muted); font-size: .85rem; margin-top: .55rem; }
41
+ footer { color: var(--muted); font-size: .82rem; margin-top: 3rem; border-top: 1px solid var(--border); padding-top: 1rem; }
42
+ </style>
43
+ </head>
44
+ <body>
45
+ <div class="wrap">
46
+ <h1>JavisDiT Edit — audio-visual object addition &amp; removal</h1>
47
+ <p class="sub">
48
+ Checkpoint <code>text_both_0721 / epoch001-global_step13000</code> (EMA) · Wan2.1-T2AV 1.3B, FiLM text conditioning,
49
+ trained on both edit directions · 81 frames @ 16 fps, 256×256, 50 sampling steps, CFG 5.0 ·
50
+ target's first frame prepended as anchor (stripped before decode). One test-set sample and one train-set sample (overfit check), each run in both directions. All clips include generated audio — unmute to listen.
51
+ </p>
52
+
53
+ <section>
54
+ <div class="sec-head">
55
+ <h2>Addition — “birds”</h2><span class="badge test">test set</span>
56
+ <span class="prompt">prompt: <code>a video with birds</code> · epMUuqXcgeo_000030</span>
57
+ </div>
58
+ <div class="row">
59
+ <div class="cell"><h3>Source (input, birds removed)</h3><video src="videos/test_add_source.mp4" controls loop muted playsinline></video></div>
60
+ <div class="cell gen"><h3>Generated (model output)</h3><video src="videos/test_add_generated.mp4" controls loop playsinline></video></div>
61
+ <div class="cell"><h3>Target (ground truth)</h3><video src="videos/test_add_target.mp4" controls loop muted playsinline></video></div>
62
+ </div>
63
+ </section>
64
+
65
+ <section>
66
+ <div class="sec-head">
67
+ <h2>Removal — “birds”</h2><span class="badge test">test set</span>
68
+ <span class="prompt">prompt: <code>a video without birds</code> · epMUuqXcgeo_000030</span>
69
+ </div>
70
+ <div class="row">
71
+ <div class="cell"><h3>Source (input, birds present)</h3><video src="videos/test_remove_source.mp4" controls loop muted playsinline></video></div>
72
+ <div class="cell gen"><h3>Generated (model output)</h3><video src="videos/test_remove_generated.mp4" controls loop playsinline></video></div>
73
+ <div class="cell"><h3>Target (ground truth)</h3><video src="videos/test_remove_target.mp4" controls loop muted playsinline></video></div>
74
+ </div>
75
+ </section>
76
+
77
+ <section>
78
+ <div class="sec-head">
79
+ <h2>Addition — “trumpet”</h2><span class="badge train">train set (overfit check)</span>
80
+ <span class="prompt">prompt: <code>a video with trumpet</code> · GfeEN8LONh0_000253</span>
81
+ </div>
82
+ <div class="row">
83
+ <div class="cell"><h3>Source (input, trumpet removed)</h3><video src="videos/train_add_source.mp4" controls loop muted playsinline></video></div>
84
+ <div class="cell gen"><h3>Generated (model output)</h3><video src="videos/train_add_generated.mp4" controls loop playsinline></video></div>
85
+ <div class="cell"><h3>Target (ground truth)</h3><video src="videos/train_add_target.mp4" controls loop muted playsinline></video></div>
86
+ </div>
87
+ </section>
88
+
89
+ <section>
90
+ <div class="sec-head">
91
+ <h2>Removal — “trumpet”</h2><span class="badge train">train set (overfit check)</span>
92
+ <span class="prompt">prompt: <code>a video without trumpet</code> · GfeEN8LONh0_000253</span>
93
+ </div>
94
+ <div class="row">
95
+ <div class="cell"><h3>Source (input, trumpet present)</h3><video src="videos/train_remove_source.mp4" controls loop muted playsinline></video></div>
96
+ <div class="cell gen"><h3>Generated (model output)</h3><video src="videos/train_remove_generated.mp4" controls loop playsinline></video></div>
97
+ <div class="cell"><h3>Target (ground truth)</h3><video src="videos/train_remove_target.mp4" controls loop muted playsinline></video></div>
98
+ </div>
99
+ </section>
100
+
101
+ <footer>
102
+ Source/target reference clips are the training latents decoded back to pixels (video VAE + AudioLDM2), so they show the same reconstruction quality ceiling the model trains against. Generated clips carry the model's generated audio track; reference clips are muted by default but also contain their decoded audio.
103
+ </footer>
104
+ </div>
105
+ </body>
106
  </html>
videos/test_add_generated.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d12820260ebd63a152aa7482ecad7d35b1959e3c77c42e540cbfec5cfa0fb11
3
+ size 666192
videos/test_add_source.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c293c29d5085778c1d6872882949651233f1d5fd142ed97ab5344bb63e4da3e
3
+ size 200222
videos/test_add_target.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fceb3cd454af472f4aa56bccdb232517a0897e12f7c96cf778736ade2549b0e
3
+ size 333393
videos/test_remove_generated.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:169fe6ea863688b8c0be16e673d6adf24af02a20924144e920b823403df89aac
3
+ size 371781
videos/test_remove_source.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fceb3cd454af472f4aa56bccdb232517a0897e12f7c96cf778736ade2549b0e
3
+ size 333393
videos/test_remove_target.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c293c29d5085778c1d6872882949651233f1d5fd142ed97ab5344bb63e4da3e
3
+ size 200222
videos/train_add_generated.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4ce56f9ccc8b7d96dbd1495ca669f1b9517ca67afed7b2b9b6d3b586a1556c
3
+ size 498762
videos/train_add_source.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a6de2ae8c2a501813bf40ffb389788557427160e2206572385a167fe7f98933
3
+ size 149098
videos/train_add_target.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1f158f9ac3e4b94e8fedf611de494c0987f792fa59325ddeb8b9abea6c76ae
3
+ size 228239
videos/train_remove_generated.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:987187a3cb2836ecaca60c1910a14c358eeff63e0129eb2fc5ce1047f099618d
3
+ size 339732
videos/train_remove_source.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1f158f9ac3e4b94e8fedf611de494c0987f792fa59325ddeb8b9abea6c76ae
3
+ size 228239
videos/train_remove_target.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a6de2ae8c2a501813bf40ffb389788557427160e2206572385a167fe7f98933
3
+ size 149098