Upload 2698739/3030557/README.md with huggingface_hub

2698739/3030557/README.md

@@ -0,0 +1,128 @@
+---
+license: other
+tags:
+- audio
+- lora
+- softly-spoken
+- style
+- whisper
+---
+
+# LTX-2.3 Whisper & Soft-Spoken Audio LoRA - v1.0 - 3030557
+
+**Model Type**: LORA
+
+**Base Model**: LTXV 2.3
+
+**Trigger Words**: None
+
+**Tags**: audio, lora, softly-spoken, style, whisper
+
+## Gallery
+
+<table>
+  <tr>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/1f6b20e4-9782-41e1-ac01-e30c2044badb/original=true/133688104.mp4" width="200" controls muted autoplay loop></video></td>
+    <td><video src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/420271c7-5ff5-4378-a996-4a1ec2d3890a/original=true/133688615.mp4" width="200" controls muted autoplay loop></video></td>
+  </tr>
+</table>
+
+## Description
+
+### LTX-2.3 Whisper & Soft-Spoken Audio LoRA
+
+**Base model:** LTX-2.3 · **Type:** Audio-style LoRA · **Rank:** 32
+
+---
+
+## What this does
+
+LTX-2.3 can generate dialogue, multi-speaker scenes, and full dynamic range audio including screaming — but it cannot whisper. This LoRA adds two quiet vocal registers to the model:
+
+- **Whispering** — devoiced, breathy, close-mic delivery
+
+- **Soft-spoken** — voiced but low-volume, intimate, relaxed
+
+The LoRA targets only the three attention modules that write to the audio branch `audio_attn1`, `audio_attn2`, `video_to_audio_attn`). Video output is provably unchanged — no visual fighting, no style drift.
+
+---
+
+## Usage
+
+Load at strength **1.0**. The register is controlled entirely by the manner keyword in your prompt — no special strength tuning needed.
+
+### Trigger words (none, use natural language)
+
+| Whispering | `(woman, whispering)` | `(man, whispering quietly)` |
+
+| Soft-spoken | `(woman, speaking softly)` | `(man, speaking softly)` |
+
+> **Note:** Male whisper may requires the extra word `quietly` to tip the model over. `(man, whispering)` alone produces soft-spoken, not true whisper.
+
+### Prompt format
+
+Follow the LTX-2.3 dialogue caption style:
+
+```
+
+a [scene description], ([gender], [manner]): "[what they say]", intimate ASMR
+
+```
+
+**Examples:**
+
+```
+
+a woman sitting close to a microphone in warm dim lighting, (woman, whispering): "close your eyes and listen"
+
+a man at a desk late at night, (man, speaking softly): "I've been thinking about this all day"
+
+a woman doing a skincare routine, (woman, whispering quietly): "this is my favourite step"
+
+```
+
+### Without manner keywords
+
+Using the LoRA without any manner keyword defaults to **soft-spoken** — a subtle volume-softening effect on whatever the base model would have generated. Useful as a gentle "quieter audio" modifier.
+
+---
+
+## What it can't do
+
+- **No intra-clip register mixing.** You can't have one character whisper and another speak normally in the same clip. The register applies to the whole generation. For mixed-register dialogue, generate each part separately and cut them together.
+
+- **No magic above the vocoder ceiling.** The audio chain passes through a mel spectrogram bottleneck. Breathy whisper HF energy gets partially smoothed. Expect intimate and quiet, not studio-crisp ASMR.
+
+- **Video is untouched by design.** If you want the visuals to also feel ASMR (soft lighting, close-up framing), describe that in the scene prompt — the LoRA won't help or hurt.
+
+---
+
+## Training details
+
+| | |
+
+|---|---|
+
+| Base model | LTX-2.3 dev |
+
+| Steps | 2000 |
+
+| Rank / Alpha | 32 / 32 |
+
+| Target modules | audio\_attn1, audio\_attn2, video\_to\_audio\_attn |
+
+| Training resolution | 192×192, 97 frames (~4s @ 24fps) |
+
+| Dataset | 74 clips, 8 voices (4F / 4M), 2 registers each |
+
+Clips were 4-second segments sourced from ASMR content across 8 speakers — 4 female (2 soft-spoken, 2 whisper) and 4 male (2 soft-spoken, 2 whisper). Captions used Whisper ASR transcription in `(gender, manner): "transcript", intimate ASMR` format.
+
+---
+
+Author: [plz12345](https://civitai.com/user/plz12345)
+
+Model: [CivitAI Model Page](https://civitai.com/models/2698739?modelVersionId=3030557)
+
+Archive: [CivArchive Page](https://civarchive.com/models/2698739?modelVersionId=3030557)
+
+<!-- Version: 20260614_upload -->