Update app.py

shrink output video, balance columns, narrow container

Update app.py

Update app.py

revert audio CSS, restore image|audio row layout

audio component: harder CSS that actually targets gradio's svelte classes

polish UI: equalize input shade, shrink audio, drop mode radio, visible progress

add FLUX.2-klein-4B Generate/Edit tab + group voice and script

Update README.md

Update README.md

Update app.py

add output duration slider (1-5s) with ffmpeg trim

fix GPU window blowout: pre-warm Perth + don't erode base with steps

faster inference: pre-warm video client, configurable TTS steps

slicker UI: dark slate theme, image+audio side-by-side, wider output

ui cleanup: trim header, fold resolution+seed into advanced, randomize seed, examples below

fix Client kwarg + drop voice presets so users clone their own voice

Merge remote-tracking branch 'origin/main'

fork dramabox into avatar-generator: chain TTS + LongCat lip-sync

initial commit

Fix ZeroGPU duration: dynamic per-sentence sizing, cap at 120s (#3)

Drop mamba-ssm / causal-conv1d from requirements

Long-form chunking + RE-USE on reference

use gradio server (#2)

Update app.py

Drop xformers: FA3 Hopper kernel crashes on ZeroGPU H200

Bump torch 2.4.0 -> 2.8.0 for ZeroGPU compat

Add 5 long-form (~30s) examples to the Gradio Examples table

Show LTX acknowledgement banner inside the Gradio app (above the fold)

Add Reference duration slider (3–30s, default 10s)

Add explicit Target Duration slider (0–60s) + gen_duration kwarg

Move LTX acknowledgement to top of Space README, position DramaBox as Resemble AI's product

Revert: keep DramaBox naming (rebrand reverted per CEO)

Rebrand: DramaBox → LTX-2.3-Voice

Patch end-of-clip silence prior at latent frame 513 for >20s outputs

Drop video_connector + video_aggregate_embed BEFORE .to(device)

Use richer duration estimator in warm server (sentence + non-verbal aware)

Warm-load TTSServer at module level (IndexTTS pattern)

Add 8 voice references + click-to-generate Examples table

Replace example dropdown with click-to-generate gr.Examples table

Default Gradio server to port 7860 (HF Spaces gateway expects this)

Pin pydantic==2.10.6 — root cause of the recurring bool-iter crash

Disable SSR + analytics + auto-API for ZeroGPU compat

Bump to gradio 5.7.1; drop pydantic/starlette/fastapi 4.x compat pins

Pin starlette<1.0 + fastapi<0.116 for gradio 4.44.1 TemplateResponse compat

Pin pydantic==2.10.6 to fix gradio_client schema bool TypeError

Pin SDK to 4.44.1 + monkey-patch gradio_client schema bool TypeError

Bump gradio to 5.x to fix gradio_client schema TypeError on bool

Pin torch/torchaudio==2.4.0 to fix ZeroGPU libcudart.so.13 mismatch

Refactor for ZeroGPU: lazy TTSServer load + @spaces.GPU decorator