ACE-Step UI: title: 'Error',

App: ACE-Step UI (ace-step-ui.pinokio.git)
Repo: https://github.com/cocktailpeanut/ace-step-ui.pinokio.git
Generated: 2026-08-11T09:15:49.460Z
Pinokio: 8.0.40
Platform: win32 x64
Node: v22.21.1

Summary

System

{
  "pinokio": {
    "version": "8.0.40",
    "node": "v22.21.1",
    "platform": "win32",
    "arch": "x64"
  },
  "hardware": {
    "gpu": "nvidia",
    "gpu_model": "nvidia geforce rtx 4050 laptop gpu",
    "ram_gb": 16,
    "vram_gb": 6
  },
  "os": {
    "platform": "Windows",
    "distro": "Microsoft Windows 11 Home Single Language",
    "release": "10.0.26200",
    "codename": "25H2",
    "kernel": "10.0.26200",
    "arch": "x64",
    "build": "26200",
    "servicepack": "0.0",
    "uefi": true
  },
  "system": {
    "manufacturer": "Acer",
    "model": "Nitro ANV15-51",
    "version": "V1.60",
    "virtual": false
  },
  "cpu": {
    "manufacturer": "Intel",
    "brand": "Gen Intel® Core™ i5-13420H",
    "vendor": "GenuineIntel",
    "family": "6",
    "model": "186",
    "stepping": "2",
    "speed": 2.1,
    "speedMin": 2.1,
    "speedMax": 2.1,
    "cores": 12,
    "physicalCores": 8,
    "processors": 1,
    "performanceCores": 12,
    "efficiencyCores": 0,
    "virtualization": true,
    "cache": {
      "l1d": 327680,
      "l1i": 393216,
      "l2": 7340032,
      "l3": 12582912
    }
  },
  "memory": {
    "total": 16869351424,
    "free": 3417911296,
    "used": 13451440128,
    "active": 13451440128,
    "available": 3417911296,
    "buffers": 0,
    "cached": 0,
    "slab": 0,
    "buffcache": 0,
    "swaptotal": 24761073664,
    "swapused": 1823473664,
    "swapfree": 22937600000
  },
  "gpus": [
    {
      "model": "nvidia geforce rtx 4050 laptop gpu"
    },
    {
      "model": "intel(r) uhd graphics"
    }
  ],
  "graphics": {
    "controllers": [
      {
        "vendor": "NVIDIA",
        "model": "NVIDIA GeForce RTX 4050 Laptop GPU",
        "bus": "PCI",
        "vram": 6141,
        "vramDynamic": false,
        "driverVersion": "610.62"
      },
      {
        "vendor": "Intel Corporation",
        "model": "Intel(R) UHD Graphics",
        "bus": "PCI",
        "vram": 2047.99609375,
        "vramDynamic": true
      }
    ],
    "displays": [
      {
        "model": "Default Monitor",
        "main": true,
        "builtin": true,
        "connection": "INTERNAL",
        "currentResX": 1920,
        "currentResY": 1080,
        "resolutionX": 1920,
        "resolutionY": 1080,
        "pixelDepth": 32,
        "currentRefreshRate": 144
      }
    ]
  }
}

Logs

logs/api/start.js/1786437401472

Source: api / start.js
Lines: 376 total, last 376 included

[api shell.run]
Microsoft Windows [Version 10.0.26200.8875]
(c) Microsoft Corporation. All rights reserved.

C:\pinokio\api\ace-step-ui.pinokio.git\app\server>conda_hook & conda deactivate & conda deactivate & conda deactivate & conda activate base && npm start

> ace-step-ui-server@1.0.0 start
> node dist/index.js

Running SQLite database migrations...
Migrations completed successfully!
ACE-Step UI Server running on http://localhost:3001
Environment: production
ACE-Step API: http://127.0.0.1:42003
LAN access: http://10.200.2.218:3001
Initializing local storage provider
Job job_1786437566391_8pqnymn: Queued at position 1
[Gradio] Connected to http://127.0.0.1:42003
Job job_1786437566391_8pqnymn: Using Gradio /generation_wrapper {
  prompt: 'Lofi R&B Pop fusion, melodic male vocals, soft pia',
  duration: undefined,
  batchSize: 1
}
Job job_1786437566391_8pqnymn: Gradio generation failed, trying Python spawn fallback {
  type: 'status',
  endpoint: '/generation_wrapper',
  fn_index: 127,
  time: 2026-08-11T08:39:26.805Z,
  original_msg: undefined,
  queue: true,
  title: 'Error',
  message: "Value:  is not in the list of choices: ['euler', 'heun']",
  visible: true,
  duration: 10,
  stage: 'error',
  code: undefined,
  success: false
}
Job job_1786437566391_8pqnymn: Using Python spawn (Gradio not available) {
  prompt: 'Lofi R&B Pop fusion, melodic male vocals, soft pia',
  lyricsPreview: '[Intro]\nWanna hold your hand,\nWanna hug you tight,',
  duration: undefined,
  batchSize: 1
}
[ACE-Step] Skipping import of cpp extensions due to incompatible torch version 2.7.1+cu128 for torchao version 0.15.0             Please see https://github.com/pytorch/ao/issues/2919 for more info
[ACE-Step] W0811 14:09:37.043000 19212 env\Lib\site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.
[ACE-Step] 2026-08-11 14:09:39.592 | WARNING  | acestep.training.trainer:<module>:40 - bitsandbytes not installed. Using standard AdamW.
[ACE-Step] 2026-08-11 14:09:39.632 | INFO     | acestep.gpu_config:get_gpu_memory_gb:578 - CUDA GPU detected: NVIDIA GeForce RTX 4050 Laptop GPU (6.0 GB)
[ACE-Step] 2026-08-11 14:09:39.778 | INFO     | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: sdpa
[ACE-Step] 2026-08-11 14:09:40.427 | INFO     | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:200 - [initialize_service] Keeping main model on cuda (persistent)
[ACE-Step] There are modules in AutoencoderOobleck that should be kept in float32: []. Casting directly with `to()` can lead to inconsistent results; set `torch_dtype` in `from_pretrained()` instead to keep these modules in float32.
[ACE-Step] 2026-08-11 14:09:48.507 | INFO     | acestep.inference:generate_music:641 - [generate_music] LLM usage decision: thinking=False, use_cot_caption=True, use_cot_language=True, use_cot_metas=True, need_lm_for_cot=True, llm_initialized=False, use_lm=False
[ACE-Step] 2026-08-11 14:09:48.510 | INFO     | acestep.core.generation.handler.generate_music:generate_music:289 - [generate_music] Turbo model detected: overriding guidance_scale 9.0 -> 1.0 (turbo does not use CFG).
[ACE-Step] 2026-08-11 14:09:48.510 | INFO     | acestep.core.generation.handler.generate_music:generate_music:304 - [generate_music] Starting generation...
[ACE-Step] 2026-08-11 14:09:48.510 | INFO     | acestep.core.generation.handler.generate_music:generate_music:307 - [generate_music] Preparing inputs...
[ACE-Step] 2026-08-11 14:09:48.511 | INFO     | acestep.core.generation.handler.generate_music_request:_prepare_reference_and_source_audio:112 - [generate_music] Processing reference audio...
[ACE-Step] 2026-08-11 14:09:48.651 | DEBUG    | acestep.core.generation.handler.io_audio:process_reference_audio:136 - [process_reference_audio] Reference audio shape: torch.Size([2, 5177344])
[ACE-Step] 2026-08-11 14:09:48.651 | DEBUG    | acestep.core.generation.handler.io_audio:process_reference_audio:139 - [process_reference_audio] Reference audio sample rate: 48000
[ACE-Step] 2026-08-11 14:09:48.651 | DEBUG    | acestep.core.generation.handler.io_audio:process_reference_audio:140 - [process_reference_audio] Reference audio duration: 107.861333 seconds
[ACE-Step] 2026-08-11 14:09:48.716 | DEBUG    | acestep.core.generation.handler.generate_music:_vram_preflight_check:132 - [generate_music] VRAM pre-flight: skipping check (offload_to_cpu=True, models loaded one-at-a-time)
[ACE-Step] 2026-08-11 14:09:48.736 | WARNING  | acestep.core.generation.handler.service_generate_request:_normalize_service_generate_inputs:53 - [service_generate] dmd_gan version: infer_steps 12 exceeds maximum 8, clamping to 8
[ACE-Step] 2026-08-11 14:09:48.812 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:41 - [_load_model_context] Loading vae to cuda (RSS: 0 MB)
[ACE-Step] There are modules in AutoencoderOobleck that should be kept in float32: []. Casting directly with `to()` can lead to inconsistent results; set `torch_dtype` in `from_pretrained()` instead to keep these modules in float32.
[ACE-Step] 2026-08-11 14:09:50.021 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:58 - [_load_model_context] Loaded vae to cuda in 0.4741s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-08-11 14:09:50.070 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:67 - [_load_model_context] Offloading vae to CPU (RSS: 0 MB)
[ACE-Step] There are modules in AutoencoderOobleck that should be kept in float32: []. Casting directly with `to()` can lead to inconsistent results; set `torch_dtype` in `from_pretrained()` instead to keep these modules in float32.
[ACE-Step] 2026-08-11 14:09:50.456 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:83 - [_load_model_context] Offloaded vae to CPU in 0.2605s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-08-11 14:09:50.500 | INFO     | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:119 - 
[ACE-Step] ======================================================================
[ACE-Step] 2026-08-11 14:09:50.500 | INFO     | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:120 - \U0001f50d [DEBUG] DiT TEXT ENCODER INPUT (Inference)
[ACE-Step] 2026-08-11 14:09:50.500 | INFO     | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:121 - ======================================================================
[ACE-Step] 2026-08-11 14:09:50.500 | INFO     | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:122 - text_prompt:
[ACE-Step] # Instruction
[ACE-Step] Fill the audio semantic mask based on the given conditions:
[ACE-Step] # Caption
[ACE-Step] Lofi R&B Pop fusion, melodic male vocals, soft piano chords, smooth bassline, atmospheric strings, chill hip-hop drums, crisp percussion
[ACE-Step] Male vocals
[ACE-Step] # Metas
[ACE-Step] - bpm: N/A
[ACE-Step] - timesignature: N/A
[ACE-Step] - keyscale: N/A
[ACE-Step] - duration: 60 seconds
[ACE-Step] <|endoftext|>
[ACE-Step] 2026-08-11 14:09:50.500 | INFO     | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:123 - ======================================================================
[ACE-Step] 2026-08-11 14:09:50.500 | INFO     | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:124 - lyrics_text:
[ACE-Step] # Languages
[ACE-Step] en
[ACE-Step] # Lyric
[ACE-Step] [Intro]
[ACE-Step] Wanna hold your hand,
[ACE-Step] Wanna hug you tight,
[ACE-Step] Wanna be with you,
[ACE-Step] For the rest of my life
[ACE-Step] [Pre Chorus]
[ACE-Step] Wanna hold your hand,
[ACE-Step] Wanna hug you tight,
[ACE-Step] Wanna be with you,
[ACE-Step] For the rest of my life
[ACE-Step] Wanna talk to you,
[ACE-Step] Wanna hear your voice,
[ACE-Step] Wanna loved you till,
[ACE-Step] The day... i... die...
[ACE-Step] [Chorus]
[ACE-Step] Till the day I die
[ACE-Step] ...day I die
[ACE-Step] Till the day I die
[ACE-Step] ...day I die
[ACE-Step] Till the day I die
[ACE-Step] ...day I die
[ACE-Step] Till the day I die
[ACE-Step] ...day I die<|endoftext|>
[ACE-Step] 2026-08-11 14:09:50.500 | INFO     | acestep.core.generation.handler.conditioning_text:_prepare_text_conditioning_inputs:125 - ======================================================================
[ACE-Step] 2026-08-11 14:09:50.521 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:41 - [_load_model_context] Loading vae to cuda (RSS: 0 MB)
[ACE-Step] There are modules in AutoencoderOobleck that should be kept in float32: []. Casting directly with `to()` can lead to inconsistent results; set `torch_dtype` in `from_pretrained()` instead to keep these modules in float32.
[ACE-Step] 2026-08-11 14:09:50.779 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:58 - [_load_model_context] Loaded vae to cuda in 0.1450s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-08-11 14:09:50.805 | INFO     | acestep.gpu_config:get_gpu_memory_gb:578 - CUDA GPU detected: NVIDIA GeForce RTX 4050 Laptop GPU (6.0 GB)
[ACE-Step] 2026-08-11 14:10:03.132 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:67 - [_load_model_context] Offloading vae to CPU (RSS: 0 MB)
[ACE-Step] There are modules in AutoencoderOobleck that should be kept in float32: []. Casting directly with `to()` can lead to inconsistent results; set `torch_dtype` in `from_pretrained()` instead to keep these modules in float32.
[ACE-Step] 2026-08-11 14:10:03.809 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:83 - [_load_model_context] Offloaded vae to CPU in 0.3990s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-08-11 14:10:03.813 | INFO     | acestep.core.generation.handler.conditioning_embed:preprocess_batch:110 - [preprocess_batch] Inferring prompt embeddings...
[ACE-Step] 2026-08-11 14:10:03.813 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:41 - [_load_model_context] Loading text_encoder to cuda (RSS: 0 MB)
[ACE-Step] 2026-08-11 14:10:04.903 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:58 - [_load_model_context] Loaded text_encoder to cuda in 0.8802s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-08-11 14:10:05.445 | INFO     | acestep.core.generation.handler.conditioning_embed:preprocess_batch:113 - [preprocess_batch] Inferring lyric embeddings...
[ACE-Step] 2026-08-11 14:10:05.446 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:67 - [_load_model_context] Offloading text_encoder to CPU (RSS: 0 MB)
[ACE-Step] 2026-08-11 14:10:06.771 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:83 - [_load_model_context] Offloaded text_encoder to CPU in 1.1491s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-08-11 14:10:06.771 | INFO     | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda))
[ACE-Step] 2026-08-11 14:10:07.136 | INFO     | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:263 - [service_generate] DiT diffusion via PyTorch (cuda)...
[ACE-Step] 2026-08-11 14:10:07.247 | INFO     | acestep.models.common.dcw_correction:__init__:98 - [DCW] Active � mode=double, scaler=0.0500, high_scaler=0.0200, wavelet='haar'
[ACE-Step] 2026-08-11 14:10:07.727 | INFO     | acestep.models.common.dcw_loader:get:84 - [DCW] Built DWT1D for wavelet='haar' (low-pass filter taps=2, device=cuda:0, dtype=torch.bfloat16).
[ACE-Step] 2026-08-11 14:10:08.762 | INFO     | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents...
[ACE-Step] 2026-08-11 14:10:08.763 | DEBUG    | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:64 - [generate_music] pred_latents: torch.Size([1, 1500, 64]), dtype=torch.bfloat16
[ACE-Step] 2026-08-11 14:10:08.763 | DEBUG    | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 0.06602025032043457, 'diffusion_time_cost': 1.5587737560272217, 'diffusion_per_step_time_cost': 0.1948467195034027, 'total_time_cost': 1.6247940063476562, 'offload_time_cost': 3.3077831268310547}
[ACE-Step] 2026-08-11 14:10:08.817 | INFO     | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE...
[ACE-Step] 2026-08-11 14:10:08.818 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:41 - [_load_model_context] Loading vae to cuda (RSS: 0 MB)
[ACE-Step] There are modules in AutoencoderOobleck that should be kept in float32: []. Casting directly with `to()` can lead to inconsistent results; set `torch_dtype` in `from_pretrained()` instead to keep these modules in float32.
[ACE-Step] 2026-08-11 14:10:09.182 | INFO     | acestep.core.generation.handler.init_service_offload_context:_load_model_context:58 - [_load_model_context] Loaded vae to cuda in 0.1971s (RSS: 0 -> 0 MB, delta: +0 MB)
[ACE-Step] 2026-08-11 14:10:09.184 | DEBUG    | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:136 - [generate_music] Before VAE decode: allocated=4.95GB, max=5.98GB
[ACE-Step] 2026-08-11 14:10:09.186 | INFO     | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 0.06 GB
[ACE-Step] 2026-08-11 14:10:09.186 | WARNING  | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:159 - [generate_music] Only 0.06 GB free VRAM; auto-enabling CPU VAE decode
[ACE-Step] 2026-08-11 14:10:09.186 | INFO     | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:165 - [generate_music] Moving VAE to CPU for decode (ACESTEP_VAE_ON_CPU=1)...
[ACE-Step] 2026-08-11 14:10:09.307 | INFO     | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:172 - [generate_music] Using tiled VAE decode to reduce VRAM usage...
[ACE-Step] 2026-08-11 14:10:09.308 | DEBUG    | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 0.30 GB
[ACE-Step] 2026-08-11 14:10:09.309 | DEBUG    | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 0.30 GB
[ACE-Step] 2026-08-11 14:10:09.309 | INFO     | acestep.core.generation.handler.vae_decode:tiled_decode:56 - [tiled_decode] chunk_size=128, offload_wav_to_cpu=True, latents_shape=torch.Size([1, 64, 1500])
[ACE-Step] 2026-08-11 14:10:09.309 | WARNING  | acestep.core.generation.handler.vae_decode_chunks:_tiled_decode_inner:39 - [tiled_decode] Reduced overlap from 64 to 32 for chunk_size=128
Job job_1786437566391_8pqnymn: Generation failed Error: Generation timed out after 600s
    at processGenerationViaPython (file:///C:/pinokio/api/ace-step-ui.pinokio.git/app/server/dist/services/acestep.js:539:19)
    at async processGeneration (file:///C:/pinokio/api/ace-step-ui.pinokio.git/app/server/dist/services/acestep.js:341:5)
    at async processQueue (file:///C:/pinokio/api/ace-step-ui.pinokio.git/app/server/dist/services/acestep.js:282:17)