darkframedude commited on
Commit
1cd09a4
·
verified ·
1 Parent(s): b03178c

docs: organization card — branding, Lost Footage, gallery

Browse files
Files changed (1) hide show
  1. README.md +51 -3
README.md CHANGED
@@ -1,10 +1,58 @@
1
  ---
2
  title: README
3
- emoji: 🔥
4
  colorFrom: gray
5
- colorTo: green
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
- Edit this `README.md` markdown file to author your organization card.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  title: README
3
+ emoji: 📼
4
  colorFrom: gray
5
+ colorTo: red
6
  sdk: static
7
  pinned: false
8
  ---
9
 
10
+ <style>
11
+ .hf-wrap { max-width: 920px; margin: 0 auto; }
12
+ .hf-hero { font-size: 1.35em; line-height: 1.45; margin: 0.25em 0 1em; color: #e8e8e8; }
13
+ .hf-grid { display: flex; flex-wrap: wrap; gap: 10px; justify-content: center; margin: 1.25em 0; }
14
+ .hf-grid img { width: 280px; max-width: 100%; height: auto; border-radius: 6px; border: 1px solid #333; object-fit: cover; aspect-ratio: 16/10; }
15
+ .hf-card { background: linear-gradient(145deg, #1a1a1f 0%, #121218 100%); border: 1px solid #2a2a32; border-radius: 10px; padding: 1rem 1.25rem; margin: 1.25em 0; }
16
+ .hf-card h3 { margin-top: 0; }
17
+ .hf-muted { color: #9ca3af; font-size: 0.95em; }
18
+ </style>
19
+
20
+ <div class="hf-wrap">
21
+
22
+ <p class="hf-hero"><strong>Darkframe AI</strong> publishes horror-native weights and tooling—found footage, analog artifacts, and presets that favor <em>tape damage over polish</em>.</p>
23
+
24
+ <p>
25
+ <a href="https://darkframe.ai"><strong>darkframe.ai</strong></a>
26
+ ·
27
+ <a href="https://huggingface.co/darkframeai">Models &amp; collections</a>
28
+ </p>
29
+
30
+ <div class="hf-card">
31
+
32
+ ### Hub releases
33
+
34
+ | | |
35
+ | --- | --- |
36
+ | **DARKFRAME — Lost Footage v1** | [Model card](https://huggingface.co/darkframeai/DARKFRAME-LostFootage-v1) · Night-vision cast, VHS glitches, grain, and claustrophobic “discovered recording” stills. Apache-2.0. |
37
+
38
+ <p class="hf-muted">Prompting notes, gallery, and file layout live on each model page.</p>
39
+
40
+ </div>
41
+
42
+ ### Visual language
43
+
44
+ Representative stills (training / eval references for Lost Footage v1):
45
+
46
+ <div class="hf-grid">
47
+ <img src="https://a6g3jvts3r6skzhw.public.blob.vercel-storage.com/found-footage/00%20-%20Copy.jpg" alt="Found footage corridor, institutional horror, tape degradation" />
48
+ <img src="https://a6g3jvts3r6skzhw.public.blob.vercel-storage.com/found-footage/2%20%284%29.jpg" alt="CRT glow, abandoned interior, analog noise" />
49
+ <img src="https://a6g3jvts3r6skzhw.public.blob.vercel-storage.com/found-footage/23.jpg" alt="Found footage mood board, grain and dread" />
50
+ </div>
51
+
52
+ ### For filmmakers & prompt engineers
53
+
54
+ We optimize for **genre-native** output: handheld framing, wrong lighting on purpose, chromatic bleed, and locations that feel like **evidence**—not hero shots.
55
+
56
+ <p class="hf-muted">New checkpoints and datasets land here first. Watch this org for releases.</p>
57
+
58
+ </div>