Commit Graph
273 Commits
Author SHA1 Message Date
Leonid PershinandClaude Opus 5 6e3273d049 deps: migrate the UI to Gradio 6
Gradio was unpinned, so a fresh install pulled Gradio 6, where
gr.Audio no longer accepts show_download_button — the UI crashed on
startup with TypeError. Move forward to Gradio 6 instead of pinning
back to 5:

- requirements: gradio>=6.0.0
- drop the removed show_download_button kwarg (4 call sites)
- requirements: transformers>=4.57.0 — Gradio 6 requires
  huggingface-hub>=1.0, which transformers==4.50.0 forbids. Only
  UMT5EncoderModel and AutoTokenizer are used, so the bump is safe.

Verified: pip check clean, UI renders and server callbacks work on
gradio 6.26.0 / transformers 5.16.1 / huggingface-hub 1.30.0.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-08 18:38:12 +03:00
Leonid PershinandClaude Opus 5 911899635a docs: add Russian README and a Windows start.bat launcher
- README_RU.md: full Russian translation, linked from README.md
- start.bat: one-click setup + launch for Windows. Finds Python 3.10+,
  creates the venv, installs PyTorch (CUDA or CPU) and ACE-Step, checks
  the GPU, then starts the web UI. Flags: --lowvram, --cpu, --share,
  --port, --device, --listen, --reinstall, --update, --setup, --help.
- Both READMEs document the launcher.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-08 18:38:05 +03:00
Gong Junmin 1bee4c9f5b Merge pull request #373 from iackov/fix/extend-mode-shape-mismatch 2026-02-15 12:57:54 +08:00
Gong Junmin 4a24cfb662 Merge pull request #375 from ace-step/copilot/add-external-link-for-model 2026-02-15 12:57:18 +08:00
copilot-swe-agent[bot]andChuxiJ 66b690b05b Add external link for ACE-Step v1.5 model
Co-authored-by: ChuxiJ <30956809+ChuxiJ@users.noreply.github.com>
2026-01-28 00:09:54 +00:00
copilot-swe-agent[bot] bf3510b949 Initial plan 2026-01-28 00:08:27 +00:00
jackj 435e9fd667 Fix: Shape mismatch in extend mode causing AssertionError
- Added automatic shape alignment for target_latents and x0
- Handles both shorter (padding) and longer (trimming) cases
- Fixes crash in extend mode with long audio files
- Minimal impact on audio quality (~0.05-0.15 sec)

Resolves issue where extend mode fails with AssertionError
when target_latents shape doesn't match x0 shape after
padding/trimming operations.
2026-01-23 23:15:42 +05:00
Gong Junmin 6ae0852b13 Merge pull request #282 from WebChatAppAi/main
Fix Incorrect Data Processing Flow in TRAIN_INSTRUCTION.md
2025-06-27 13:46:58 +08:00
WebChatAppAi 6e93273e81 Update TRAIN_INSTRUCTION.md
- Corrected file format requirements and naming conventions
2025-06-27 03:11:04 +06:00
WebChatAppAi faba128c5d Update TRAIN_INSTRUCTION.md 2025-06-27 03:09:42 +06:00
Gong Junmin d612523f50 Merge pull request #257 from SD-inst/ogg-fix 2025-06-04 08:46:37 +08:00
rkfg 9c5c92946d Use sox backend for ogg 2025-06-03 15:31:20 +03:00
Gong Junmin 0440ca24bb Merge pull request #256 from ace-step/update_tech_report_link
update tech report
2025-06-03 14:22:24 +08:00
chuxij 4a328731b8 update tech report 2025-06-03 06:21:26 +00:00
Gong Junmin 1028991adc Merge pull request #254 from ace-step/add_tech_report
add tech report
2025-06-02 11:05:06 +08:00
chuxij 40f010d9f7 add tech report 2025-06-02 03:03:32 +00:00
Sayo 4db9a5db12 Merge pull request #241 from ace-step/sayo_dev
[fix] export_quantized_weights import
2025-05-26 11:40:32 +08:00
Sayo 3e2cb3ee58 [fix] export_quantized_weights import 2025-05-26 03:40:01 +00:00
Gong Junmin f995fc2715 Merge pull request #233 from SamratBarai/patch-1 2025-05-24 09:58:57 +08:00
Samrat Barai 879e717c83 Update inference.ipynb to fix bug and improve UI
There was a problem in the script that caused two lines to be merged. Fixed the problem.

Also added some emojis to the cells
2025-05-23 17:52:35 +06:00
sean d2a13e52f4 Merge pull request #230 from ace-step/dev
fix bug caused by parameter positions in infer.py
2025-05-22 15:15:34 +08:00
sean 022a72881f fix bug caused by parameter postions in infer.py 2025-05-22 07:08:45 +00:00
Gong Junmin 6f5c0f88a7 Merge pull request #229 from SD-inst/lora-weight-fix 2025-05-22 09:46:38 +08:00
rkfg 05e641f6ec Fix lora reloading on weight change 2025-05-21 19:41:11 +03:00
Gong Junmin 2ba06ca1f8 Merge pull request #221 from SD-inst/lora-weight 2025-05-20 14:42:42 +08:00
rkfg fc984d81fa Add lora weight 2025-05-20 08:59:00 +03:00
Gong Junmin 969c6739bc Merge pull request #219 from craftmine1000/main 2025-05-20 07:26:54 +08:00
Michael Hedman 12bcab346e revert unlocking dependencies 2025-05-19 16:55:01 +02:00
Michael Hedman b4ea314e1c change normal notebook repo source to official repo 2025-05-19 15:49:00 +02:00
Michael Hedman 2c120c4808 change colab notebook repo source to official repo 2025-05-19 15:41:39 +02:00
Michael Hedman 9be6e4a905 Merge branch 'main' of https://github.com/ace-step/ACE-Step.git 2025-05-19 13:55:41 +02:00
Michael Hedman 1176d3bf97 unlock dependencies for future versions 2025-05-19 13:54:42 +02:00
Michael Hedman 730340f14a bump diffusers>=0.33.0 to prevent diffusers==0.32.2 dtype casting issue 2025-05-19 13:52:22 +02:00
Gong Junmin 516792aa82 Merge pull request #214 from craftmine1000/main 2025-05-19 17:50:15 +08:00
Gong Junmin f51063ee8b Merge pull request #215 from SD-inst/diffusers-fix 2025-05-19 17:48:52 +08:00
rkfg 481d950db4 Fix lora loading with diffusers 0.33.1 2025-05-19 09:33:56 +03:00
Michael Hedman bfac11fecf prepare for hub download of quantized models 2025-05-19 08:18:26 +02:00
Michael Hedman 401b910936 missed a dtype
cleanup immediate surroundings
2025-05-19 07:57:05 +02:00
Michael Hedman 0b379b6163 reduce device and dtype vars 2025-05-19 07:34:13 +02:00
Michael Hedman d470cd903f reduce path vars 2025-05-19 06:47:04 +02:00
Michael Hedman 21efcd3905 move language filters 2025-05-19 04:51:22 +02:00
Michael Hedman cdab63d688 remove fixed float16 COLAB_FREE env var
add ACE_PIPELINE_DTYPE env var dtype config
set colab notebook to float16
2025-05-19 04:17:38 +02:00
Michael Hedman e2efc727e9 update colab notebook 2025-05-19 03:31:40 +02:00
Michael Hedman 0e0021d754 Merge branch 'main' of https://github.com/ace-step/ACE-Step.git 2025-05-18 20:22:46 +02:00
Gong Junmin 74121a5d8a Merge pull request #209 from GeorgeDrb/memory-optimization 2025-05-18 21:24:42 +08:00
GeorgeDrb 375431486c Add memory cleanup to prevent VRAM overflow 2025-05-18 15:35:21 +03:00
Gong Junmin a3a853e13d Merge pull request #207 from rsxdalv/patch-2
bump version due to new features
2025-05-18 20:12:41 +08:00
Gong Junmin ab1e3d9166 Merge pull request #208 from ace-step/revert-199-feature/#194
Revert "#194: implement negative tags for text2audio"
2025-05-18 19:42:47 +08:00
Gong Junmin e3a6f4f659 Revert "#194: implement negative tags for text2audio" 2025-05-18 19:42:29 +08:00
Roberts Slisans 7453602789 bump version due to new features
when installing the package, not updating the version number causes pip not to install the update
2025-05-18 13:39:52 +03:00