{"schema":"record/v1","id":"src_01M569EH7T3ETK0TS4BRR8QX9A","type":"source","revision":2,"etag":"\"r2.s0\"","title":"ACE-Step 1.5","summary":null,"status":"active","body":{"text":"Successor line to ace-step/ACE-Step v1 (Apache-2.0, last push 2026-02-15); GitHub does not mark it a fork. Speed/quality figures are README claims, not tested.","archived":false,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Open music foundation model v1.5 for consumer hardware: full songs of 10 s to 10 min, claimed under 2 s per song on an A100, LoRA training from ~8 songs, track separation, XL 4B DiT variants (2026-04). Repo is MIT; weights and training-data rights need separate checking.","source_type":"repository","availability":"available","dependencies":[],"source_owner":"ACE-Step team","canonical_url":"https://github.com/ace-step/ace-step-1.5","next_check_at":"2026-10-18T00:00:00.000Z","successor_url":null,"hardware_notes":"README: <4 GB VRAM claim for base; 12-20 GB for XL models.","known_limitations":[],"upstream_updated_at":"2026-10-11T14:11:22.000Z"},"categories":["T14"],"tags":["level:frontier","music-generation","local","lora","stem-separation","mit","frontier","code:python"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"reported_by_source","review":"unreviewed","review_revision":null,"claims":[{"url":"https://github.com/ace-step/ACE-Step-1.5","claim":"README: ACE-Step v1.5 is an open-source music foundation model claiming quality beyond most commercial music models (between Suno v4.5 and v5), under 2 seconds per full song on an A100 and under 10 seconds on an RTX 3090, running locally with less than 4GB VRAM.","locator":"README, abstract and features","classification":"upstream_claim"},{"url":"https://github.com/ace-step/ACE-Step-1.5","claim":"README news 2026-04-02: ACE-Step 1.5 XL (4B DiT) released, ~9 GB VRAM for weights (vs ~4.7 GB for 2B), needing >=12 GB with offload+quantization or >=20 GB without; features include 10 s to 10 min generation, LoRA training (8 songs, 1 hour on a 3090 12GB) and track separation.","locator":"README, News and feature table","classification":"upstream_claim"},{"url":"https://github.com/ace-step/ACE-Step-1.5","claim":"README License & Disclaimer: project licensed under MIT; acknowledges risks of unintentional copyright infringement from stylistic similarity and misuse; Python 3.11-3.12, CUDA recommended, also MPS/ROCm/Intel XPU/CPU.","locator":"README, License & Disclaimer; Requirements","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"MIT per README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/ace-step/ACE-Step-1.5/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README license statement refers to the project; Hugging Face weight cards and training-data provenance were not inspected.","hosting":"unknown","component":"model_weights","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/ace-step/ACE-Step-1.5"],"model_training":"unknown","redistribution":"unknown"}],"attribution":{"origin":"research_agent","upstream_owner":"ACE-Step team","upstream_url":"https://github.com/ace-step/ace-step-1.5","imported_from":"content/seeds/research/curated/resources.jsonl#ace-step--ace-step-1.5","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"ace-step--ace-step-1.5","name":"ACE-Step 1.5","tags":["level:frontier","music-generation","local","lora","stem-separation","mit","frontier"],"notes":"Successor line to ace-step/ACE-Step v1 (Apache-2.0, last push 2026-02-15); GitHub does not mark it a fork. Speed/quality figures are README claims, not tested.","rights":[{"notes":"MIT per README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/ace-step/ACE-Step-1.5/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README license statement refers to the project; Hugging Face weight cards and training-data provenance were not inspected.","hosting":"unknown","component":"model_weights","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/ace-step/ACE-Step-1.5"],"model_training":"unknown","redistribution":"unknown"}],"archived":false,"evidence":[{"url":"https://github.com/ace-step/ACE-Step-1.5","claim":"README: ACE-Step v1.5 is an open-source music foundation model claiming quality beyond most commercial music models (between Suno v4.5 and v5), under 2 seconds per full song on an A100 and under 10 seconds on an RTX 3090, running locally with less than 4GB VRAM.","locator":"README, abstract and features","classification":"upstream_claim"},{"url":"https://github.com/ace-step/ACE-Step-1.5","claim":"README news 2026-04-02: ACE-Step 1.5 XL (4B DiT) released, ~9 GB VRAM for weights (vs ~4.7 GB for 2B), needing >=12 GB with offload+quantization or >=20 GB without; features include 10 s to 10 min generation, LoRA training (8 songs, 1 hour on a 3090 12GB) and track separation.","locator":"README, News and feature table","classification":"upstream_claim"},{"url":"https://github.com/ace-step/ACE-Step-1.5","claim":"README License & Disclaimer: project licensed under MIT; acknowledges risks of unintentional copyright infringement from stylistic similarity and misuse; Python 3.11-3.12, CUDA recommended, also MPS/ROCm/Intel XPU/CPU.","locator":"README, License & Disclaimer; Requirements","classification":"sourced_fact"}],"language":"Python","checked_on":"2026-10-17","usefulness":"Open music foundation model v1.5 for consumer hardware: full songs of 10 s to 10 min, claimed under 2 s per song on an A100, LoRA training from ~8 songs, track separation, XL 4B DiT variants (2026-04). Repo is MIT; weights and training-data rights need separate checking.","source_type":"repository","category_ids":["T14"],"source_owner":"ACE-Step team","canonical_url":"https://github.com/ace-step/ACE-Step-1.5","review_status":"reviewed","hardware_notes":"README: <4 GB VRAM claim for base; 12-20 GB for XL models.","schema_version":"0.1","execution_status":"reported_by_source","inspection_status":"source_inspected","upstream_updated_at":"2026-10-11T14:11:22Z","proposed_next_action":"reproduce"},"collector":{"file":"research-results/_inbox/lane-c/T14.json","lane":"lane-c","branch":"worktree-agent-a05d50ee98f3b389b","commit":"33f3b9d","collector":"Claude Sonnet 5.5 (high), combined lane C (T10-T14), founder-run","file_sha256":"59266c5069dfce174c081d415431cea23c66278e285dc3580ff4f6b17a356e4b","merged_from":[],"original_id":"ace-step--ace-step-1.5","review_reason":"L07 review 2026-10-17: lane lane-c accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"ace-step--ace-step-1.5","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"Python","execution_status":"reported_by_source","inspection_status":"source_inspected","proposed_next_action":"reproduce"},"source_schema":"resource-candidate/0.1","original_sha256":"eb6363c85d2f9ca88d0011662d4749f1f139e6126ceebafcc9000934609ac593","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569EH7T3ETK0TS4BRR8QX9A","api_url":"https://veyrul.com/v1/records/src_01M569EH7T3ETK0TS4BRR8QX9A","created_at":"2026-10-18T01:19:04.429Z","updated_at":"2026-10-18T01:23:56.373Z","last_activity_at":"2026-10-18T01:23:56.373Z"}