vh5tape VHS LoRA — final 5000-step checkpoint, card, gallery

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+samples/cartoon-robot.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/commercial-toy.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/game-arcade.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/movie-horror.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/musicvideo.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/news-anchor.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/vh5-commercial.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,120 @@
+---
+license: other
+license_name: minimax-h3-community-license
+license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
+base_model: MiniMaxAI/MiniMax-H3
+pipeline_tag: text-to-video
+tags:
+- lora
+- video
+- text-to-video
+- vhs
+- retro
+- 1980s
+- style
+- minimax-h3
+---
+
+# vh5tape — a worn-VHS look for MiniMax H3
+
+A style LoRA that makes H3 footage look like it was recorded off 1980s broadcast
+television onto a VHS tape that has seen better days — soft smeared detail, chroma
+bleed, tracking noise, head-switching bands at the frame edge, and (because H3
+trains audio jointly) the matching muffled mono sound, tape hiss and warble.
+
+The damage is a **prompt-controlled dial** with three trained levels, from a gentle
+analog glow to a tape the VCR can barely hold onto.
+
+## Gallery
+
+All clips are raw single takes at 480P / 4:3 — none of this content was in the
+training data.
+
+<table>
+<tr>
+<td><video controls muted loop src="samples/cartoon-robot.mp4"></video></td>
+<td><video controls muted loop src="samples/news-anchor.mp4"></video></td>
+</tr>
+<tr>
+<td><video controls muted loop src="samples/game-arcade.mp4"></video></td>
+<td><video controls muted loop src="samples/movie-horror.mp4"></video></td>
+</tr>
+<tr>
+<td><video controls muted loop src="samples/commercial-toy.mp4"></video></td>
+<td><video controls muted loop src="samples/musicvideo.mp4"></video></td>
+</tr>
+</table>
+
+And a commercial for the tape itself, rendered by the tape itself:
+
+<video controls muted loop src="samples/vh5-commercial.mp4"></video>
+
+## Prompting
+
+Prompt the way the model was trained: **trigger first, damage tier second, scene third.**
+
+```
+vh5tape, badly damaged VHS tape with heavy tracking errors and distortion. A loud
+1980s local used car commercial: a salesman in a plaid suit shouts at a car lot
+with strings of pennant flags and a spinning price sign, cheesy synthesizer
+jingle, echoing announcer voice.
+```
+
+### The damage dial
+
+| level | phrase |
+|---|---|
+| light | `lightly worn VHS tape with slight analog noise` |
+| medium | `worn VHS tape recording with visible tape damage` |
+| heavy | `badly damaged VHS tape with heavy tracking errors and distortion` |
+
+### Tips
+
+- **Trigger**: `vh5tape` — put it at the very start of the prompt.
+- **Prompt expansion**: the LoRA was trained through H3's caption format, and the
+  `balanced` expansion mode preserves the trigger and damage phrases — safe to keep on.
+- **Scale**: `1.0` for the full look; `0.7–0.9` softens the wear if heavy prompts
+  overshoot; up to `~1.5` pushes toward barely-watchable tape (fun for horror).
+- **Sound comes along for free**: describe the audio ("muffled mono audio",
+  "canned laughter", "cheesy jingle") and it renders appropriately tape-worn.
+- **Dialogue**: give characters short explicit quoted lines
+  (`the host says: "It slices, it dices!"`) — they come through near-verbatim.
+- Period set dressing helps: wood paneling, studio lighting, 4:3, era wardrobe.
+
+## Recipe (fal)
+
+Works on the H3 and H3-Max LoRA endpoints
+(`minimax/h3/text-to-video/lora`, `minimax/h3-max/text-to-video/lora`) and their
+image-to-video LoRA siblings:
+
+```json
+{
+  "prompt": "vh5tape, worn VHS tape recording with visible tape damage. A 1980s ...",
+  "loras": [{ "path": "<url to vh5tape.safetensors>", "scale": 1.0 }],
+  "resolution": "480P",
+  "aspect_ratio": "4:3",
+  "duration": 15,
+  "prompt_expansion_mode": "balanced"
+}
+```
+
+480P / 4:3 is the period-correct sweet spot; the style carries fine to higher
+resolutions if you want clean pixels of a dirty tape.
+
+## Training
+
+Trained with fal's MiniMax H3 t2v trainer (rank 32, 5,000 steps, 4:3, joint
+video+audio objective) on a small hand-curated set of four-second clips of period
+broadcast material — sitcoms, soap operas, commercials, news and station
+sign-offs — each captioned with its content and one of the three damage-tier
+phrases above. The 5,000-step checkpoint beat its 2k/3k/4k/6k siblings in blind
+A/B testing; more steps past 5k made the damage *tamer*, not heavier.
+
+## Get the weights
+
+| file | what |
+|---|---|
+| [`vh5tape.safetensors`](./vh5tape.safetensors) | the LoRA, rank 32, 5,000 steps |
+
+Made for **H3-TV** — a 1970s portable CRT being rebuilt to play an endless,
+slightly wrong 1980s broadcast day.

samples/cartoon-robot.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c7a567b40668601d9f686fc56b04b9fd04ced81d06c5776bc55cec427c846b
+size 7809251

samples/commercial-toy.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f35dd3e985739f053dab32d3c700f2d4a228e99c4a739cc657472e7e147d72d4
+size 6380145

samples/game-arcade.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d765a9580ab3d6f39e219c06d0b4e2753372d3a37f28da2d7e30d4bb250eba6b
+size 4581365

samples/movie-horror.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d30cc474e9e19ecf1c445e6ab10a40ea5d8ec7f09edb9daff08e8ad51e4187
+size 4985254

samples/musicvideo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd31159aa9e5099ec8948a3256ab2754d0ecd4a8d15020dea389e28fd921d09
+size 5449396

samples/news-anchor.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38586d6cb4a885c26e4b8fb08981590cee4f4a034f338d91958a81865dddab5
+size 3142994

samples/vh5-commercial.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c8e1730fc0792019cf951146be2e77118b196181a202204402b1557d20c5c3
+size 7787796

vh5tape.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77f68c0203360a2ce6730cc2b237c61e59f5136937f525ff2d1069d292684a2
+size 131229760