Commit Graph

10 Commits

Author SHA1 Message Date
fspecii 8433349af5 Add AI Enhance toggle for better genre accuracy
When enabled, uses the LLM to enrich genre/style tags into detailed
music descriptions and generate proper BPM, key, and time signature
metadata (CoT features). Fixes genre tags like "pop, rock" producing
ballad-like output by matching Gradio UI default behavior.

- Add enhance toggle in Style of Music card header
- Gate CoT metas/caption/language by enhance OR thinking flag
- Remove unsupported --lm-backend/--lm-model from Python fallback
- Add i18n translations (en/zh/ja/ko) with tooltip
2026-02-10 13:24:36 +02:00
fspecii 565faacb7b Gradio API migration, training pipeline, news page, and UI improvements
- Migrate backend from REST API to Gradio @gradio/client for generation
- Fix Gradio parameter alignment (positions 36-49) for reference/cover audio
- Add LoRA training pipeline with dataset upload, preprocessing, and export
- Add News page with dismiss/restore and GitHub star button
- Add localization info icon in Settings language section
- Fix upload audio URL prefix, add missing MIME types
- Add training API routes and Python preprocess script
- Update i18n with news keys for all languages
2026-02-09 22:30:15 +02:00
fspecii b00af8a704 i18n CreatePanel with genre picker, model selector, EditableSlider, and LoRA panel
Phase 4.3: Largest component change. Adds cascading genre picker using
Phase 3 style data, DiT model selector with backend sync, EditableSlider
for all numeric parameters, LoRA load/unload panel, bulk generate, vocal
gender selector. Batch size max kept at 4 (not 8), inference steps max
kept at 32 (not 200) to prevent OOM. Added LoRA API stubs to api.ts.
Added ditModel to GenerationParams type.
2026-02-08 18:41:14 +02:00
fspecii 325046eaf2 Apply i18n to all components, add collapsible sidebar, playback speed control, inline title editing, and ConfirmDialog for deletions
Phase 4: i18n all 15 components from PR #19. Sidebar gains collapse/expand
toggle. Player gets playback speed selector (0.25x-2.0x) fixing bug B1
(hardcoded Chinese '正常'). SongList adds inline title editing and model
version badge. Delete actions now use ConfirmDialog instead of
window.confirm. Volume persisted to localStorage. Training nav item
deferred to Phase 7.
2026-02-08 18:35:09 +02:00
fspecii 6f4d50ae18 Add LM Model selector (0.6B/1.7B/4B) with auto-download
- Add lmModel parameter through full chain (types, API, routes, service)
- Add LM Model dropdown in Advanced Settings (defaults to 0.6B)
- Pass lmModel and lmBackend to format/enhance endpoint
- Update format_sample.py to accept --lm-model and --lm-backend args
- Auto-download model from HuggingFace if not present locally
- Persist model selection in localStorage
- Improve format route error logging with exit code and stdout/stderr

Fixes #9
2026-02-05 23:55:55 +02:00
fspecii 58d00a23ed Merge PR #24: Various UI improvements from riversedge
Includes progress bar, drag and drop, gender buttons, upload
improvements, and dynamic duration limits.
2026-02-05 22:34:07 +02:00
fspecii d05c665f4d Add LM Backend selector (PT vs VLLM) to reduce VRAM usage
PT backend uses ~1.6 GB VRAM vs ~9.2 GB for VLLM, making it accessible
on lower-end GPUs. Adds dropdown in Advanced Settings defaulting to PT.
2026-02-05 22:30:23 +02:00
riversedge 424bd3fd25 Various UI improvements 2026-02-04 23:15:00 -05:00
riversedge b75bea3860 Progress bar and song reference/cover metadata 2026-02-04 20:40:38 -05:00
fspecii 44f7563014 Initial commit: ACE-Step UI - Open source music generation interface 2026-02-04 03:09:38 +02:00