---
license: other
license_name: minimax-h3-community-license
license_link: https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/LICENSE
base_model: MiniMaxAI/MiniMax-H3
base_model_relation: adapter
pipeline_tag: image-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.

<video controls playsinline width="720" src="https://huggingface.co/KennethFal/vh5tape-vhs-lora-minimax-h3/resolve/main/samples/vh5-trailer.mp4"></video>

## 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 playsinline width="350" src="https://huggingface.co/KennethFal/vh5tape-vhs-lora-minimax-h3/resolve/main/samples/cartoon-robot.mp4"></video></td>
<td><video controls muted loop playsinline width="350" src="https://huggingface.co/KennethFal/vh5tape-vhs-lora-minimax-h3/resolve/main/samples/news-anchor.mp4"></video></td>
</tr>
<tr>
<td><video controls muted loop playsinline width="350" src="https://huggingface.co/KennethFal/vh5tape-vhs-lora-minimax-h3/resolve/main/samples/game-arcade.mp4"></video></td>
<td><video controls muted loop playsinline width="350" src="https://huggingface.co/KennethFal/vh5tape-vhs-lora-minimax-h3/resolve/main/samples/movie-horror.mp4"></video></td>
</tr>
<tr>
<td><video controls muted loop playsinline width="350" src="https://huggingface.co/KennethFal/vh5tape-vhs-lora-minimax-h3/resolve/main/samples/commercial-toy.mp4"></video></td>
<td><video controls muted loop playsinline width="350" src="https://huggingface.co/KennethFal/vh5tape-vhs-lora-minimax-h3/resolve/main/samples/musicvideo.mp4"></video></td>
</tr>
</table>

## 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.

## ComfyUI

`vh5tape.safetensors` loads in ComfyUI as-is — no conversion needed. It uses the
ComfyUI-native key layout (`diffusion_model.blocks.N.attn.{qkv_proj,out_proj}`,
fused QKV, alpha = rank), so all 104 modules load with no warnings.

**Base checkpoint — this is the thing that matters.** Use a non-pruned,
non-rotated base:

- ✅ `minimax_h3_fl2va_bf16.safetensors` (recommended)
- ✅ `minimax_h3_fl2va_pruned_fp8_scaled.safetensors`
- ❌ `*_int8_convrot`, `nvfp4`, `w4a8` — these store weights in a rotated /
  quantized basis. The LoRA loads without any error and then produces warped
  faces, melting limbs and disappearing objects. **The default checkpoint in the
  official ComfyUI H3 tutorial is `minimax_h3_fl2va_pruned_int8_convrot` — you
  must change it.** (Not specific to this LoRA — MiniMax-H3 LoRAs in general are
  made for fp16/fp8 bases.)

**Setup**

1. Put `vh5tape.safetensors` in `ComfyUI/models/loras/`.
2. `UNETLoader` (bf16 or fp8_scaled fl2va) → `LoraLoaderModelOnly` →
   `MiniMaxH3ImageToVideo` / your sampler.
3. Strength **1.0** (useful range 0.7–1.2).

**Sampling recipe** — H3 is CFG-distilled, so SDXL/Flux habits will degrade it
with or without a LoRA: use **BasicGuider** (not CFGGuider), `res_multistep` +
`simple`, ~**20 steps**, **video shift 12 / audio shift 3** (the MiniMax H3
Sigma Shift node). Stay near 1 MP (very low resolutions are unstable) and keep
prompts to a single shot.

**Stacking with a turbo LoRA:** drop this one to **0.4–0.6** — the two
perturbations add, and 4-step turbo has little headroom. (The `turbo_mode`
checkbox occupies its own LoRA slot; add a second `LoraLoaderModelOnly` for
this one.) 4-step turbo also softens the tape grain — ~20–25 full-precision
steps show the style best.

**If it looks wrong, two 2-minute checks:** (1) watch the console at load —
this LoRA should patch with **zero** "lora key not loaded" lines; (2) on a
quantized base, load the LoRA at **strength 0.0** and compare to no-LoRA — if
output degrades even at 0.0, the damage is the quantize→merge→requantize
round-trip on your base checkpoint, not this LoRA: switch to the bf16 base.

`vh5tape-comfyui.safetensors` is an optional convenience build: bit-identical
weights plus explicit `.alpha` tensors (= rank, scale 1.0) and the base-model
requirement in its metadata — same look, just harder to mis-load in
third-party loaders.

## 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 |
| [`vh5tape-comfyui.safetensors`](./vh5tape-comfyui.safetensors) | same weights bit-exact + explicit alpha tensors, for ComfyUI (see the ComfyUI section) |
| [`PROMPTS.md`](./PROMPTS.md) | the exact prompts + seeds behind every sample above |

Made for **H3-TV** — a 1970s portable CRT being rebuilt to play an endless,
slightly wrong 1980s broadcast day.