Generation timed out, error "Value 3 is greater than maximum value 1.0."

[kelynot]

Just installed via pinokio, tried several times with different settings

Main problem is that generation is getting timed out with no result at all

Acestep1.5-turbo Tried every lm model (lightest - hq)

there is terminal output: [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] W0504 08:42:23.758000 12940 env\Lib\site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs. [ACE-Step] 2026-05-04 08:42:25.860 | WARNING | acestep.training.trainer::40 - bitsandbytes not installed. Using standard AdamW. [ACE-Step] 2026-05-04 08:42:25.895 | INFO | acestep.gpu_config:get_gpu_memory_gb:578 - CUDA GPU detected: NVIDIA GeForce GTX 1660 Ti (6.0 GB) [ACE-Step] 2026-05-04 08:42:25.895 | INFO | acestep.core.generation.handler.init_service_orchestrator:initialize_service:96 - [initialize_service] Pre-Ampere CUDA detected: using float16 instead of bfloat16. [ACE-Step] 2026-05-04 08:42:25.971 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:151 - [initialize_service] Pre-Ampere CUDA detected: using eager attention for float16 numerical stability. [ACE-Step] 2026-05-04 08:42:25.971 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:174 - [initialize_service] Attempting to load model with attention implementation: eager [ACE-Step] 2026-05-04 08:42:28.389 | INFO | acestep.core.generation.handler.init_service_loader:_load_main_model_from_checkpoint:200 - [initialize_service] Keeping main model on cuda (persistent) [ACE-Step] 2026-05-04 08:42:38.067 | INFO | acestep.inference:generate_music:489 - [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] 2026-05-04 08:42:52.031 | 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] 2026-05-04 08:42:53.145 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:83 - [_load_model_context] Offloaded text_encoder to CPU in 0.9053s (RSS: 0 -> 0 MB, delta: +0 MB) [ACE-Step] 2026-05-04 08:42:53.145 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:161 - [service_generate] Generating audio... (DiT backend: PyTorch (cuda)) [ACE-Step] 2026-05-04 08:42:55.487 | INFO | acestep.core.generation.handler.service_generate_execute:_execute_service_generate_diffusion:259 - [service_generate] DiT diffusion via PyTorch (cuda)... [ACE-Step] 2026-05-04 08:42:57.741 | INFO | acestep.models.common.dcw_correction:init:98 - [DCW] Active � mode=double, scaler=0.0500, high_scaler=0.0200, wavelet='haar' [ACE-Step] 2026-05-04 08:43:02.732 | WARNING | acestep.models.common.dcw_loader:_try_import:39 - DCW is enabled but 'pytorch_wavelets' is not installed. Install with pip install pytorch_wavelets PyWavelets to use Differential Correction in Wavelet domain. Falling back to no-op for this generation. [ACE-Step] 2026-05-04 08:43:28.141 | INFO | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:42 - [generate_music] Model generation completed. Decoding latents... [ACE-Step] 2026-05-04 08:43:28.142 | 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.float16 [ACE-Step] 2026-05-04 08:43:28.142 | DEBUG | acestep.core.generation.handler.generate_music_decode:_prepare_generate_music_decode_state:65 - [generate_music] time_costs: {'encoder_time_cost': 1.0922296047210693, 'diffusion_time_cost': 31.561824321746826, 'diffusion_per_step_time_cost': 3.9452280402183533, 'total_time_cost': 32.654053926467896, 'offload_time_cost': 3.820669651031494} [ACE-Step] 2026-05-04 08:43:29.799 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:127 - [generate_music] Decoding latents with VAE... [ACE-Step] 2026-05-04 08:43:29.800 | 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] 2026-05-04 08:43:30.377 | INFO | acestep.core.generation.handler.init_service_offload_context:_load_model_context:58 - [_load_model_context] Loaded vae to cuda in 0.4013s (RSS: 0 -> 0 MB, delta: +0 MB) [ACE-Step] 2026-05-04 08:43:30.464 | DEBUG | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:136 - [generate_music] Before VAE decode: allocated=4.79GB, max=5.61GB [ACE-Step] 2026-05-04 08:43:30.464 | INFO | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:154 - [generate_music] Effective free VRAM before VAE decode: 0.16 GB [ACE-Step] 2026-05-04 08:43:30.464 | WARNING | acestep.core.generation.handler.generate_music_decode:_decode_generate_music_pred_latents:159 - [generate_music] Only 0.16 GB free VRAM; auto-enabling CPU VAE decode [ACE-Step] 2026-05-04 08:43:30.465 | 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] 2026-05-04 08:43:30.767 | 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] 2026-05-04 08:43:30.768 | DEBUG | acestep.core.generation.handler.memory_utils:_get_auto_decode_chunk_size:108 - [_get_auto_decode_chunk_size] Effective free VRAM: 0.46 GB [ACE-Step] 2026-05-04 08:43:30.770 | DEBUG | acestep.core.generation.handler.memory_utils:_should_offload_wav_to_cpu:131 - [_should_offload_wav_to_cpu] Effective free VRAM: 0.46 GB [ACE-Step] 2026-05-04 08:43:30.770 | 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] 2026-05-04 08:43:30.770 | 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_1777873329405_bjganf2: Generation failed Error: Generation timed out after 600s at processGenerationViaPython (D:\pinokio\api\ace-step-ui.pinokio.git\app\server\src\services\acestep.ts:723:13) at async processGeneration (D:\pinokio\api\ace-step-ui.pinokio.git\app\server\src\services\acestep.ts:507:3) at async processQueue (D:\pinokio\api\ace-step-ui.pinokio.git\app\server\src\services\acestep.ts:432:9)