Qwen 1.7b Ace15.safetensors
This repository contains one safetensors artifact from the Daniel Media Studio model archive. It is intentionally separated from the other archive entries so the file, provenance, license evidence, and usage notes...
Runtime profile
- Access
- External workflow
- Status
- Listed
- Version
- qwen_1.7b_ace15
- Source
- Hugging Face
- Updated
- Oct 1, 2026
Source description
ACE-Step 1.5 Qwen 1.7B text encoder
This repository contains one safetensors artifact from the Daniel Media Studio model archive. It is intentionally separated from the other archive entries so the file, provenance, license evidence, and usage notes are reviewable on one page.
Artifact
- File: 'qwen_1.7b_ace15.safetensors'
- Size: 3708523360 bytes
- SHA-256: 'ed63e9247d1f55f3ace04fa11e95b085fc82d459c82c5626f0b2e37b91ebd710'
- Role: music generation text encoder component
- Creator or upstream attribution: Comfy-Org repack; ACE-Step upstream
How to use it
This repository is an archive of the component, not a guaranteed standalone pipeline. Place the file in the model directory expected by the matching workflow, then load the recorded base model, VAE, tokenizer, ControlNet, or other companions. LoRA files must be attached to a compatible base pipeline; VAE and encoder files must be selected in the matching workflow; checkpoint shards must remain together with their index and companion shards.
Required companions
- acestep_v1.5_base.safetensors
- acestep_v1.5_turbo.safetensors
- ACE-Step VAE, codec, tokenizer, and workflow
DMS note
DMS integration is archive-only. Use the DMS workflow catalog and broker-controlled job path to select this artifact. Do not assume a component can generate media by itself.
Provenance
Source repositories
- Comfy-Org/ace_step_1.5_ComfyUI_files
Source URLs
- https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_1.7b_ace15.safetensors
- https://huggingface.co/ACE-Step/Ace-Step1.5
License and attribution
Recorded license: Apache-2.0 repack plus upstream ACE-Step MIT terms. See LICENSE.txt and source/ for preserved evidence.
The original-author material preserved under source/ is included for attribution and usage context. No new ownership claim is made over the upstream model, workflow, images, or documentation.
What you need
Hardware and download-size estimates are not available yet.
Requirements
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
Use this ACE-Step 1.5 workflow to make music from a style description and lyrics, with a chosen duration and seed; it saves the generated audio as an MP3.
Flow
It encodes the text, samples audio with the ACE-Step model, decodes the result to audio, and sends it to MP3 saving.
Inputs and outputs
The MP3 save node targets the `audio/ComfyUI` folder.
Setup
For ComfyUI, put the model files in `models/diffusion_models`, `models/text_encoders`, and `models/vae`, as shown in the workflow notes.
Suggestion · not verified
Dependencies
The workflow references `acestep_v1.5_turbo.safetensors`, `ace_1.5_vae.safetensors`, `qwen_0.6b_ace15.safetensors`, and `qwen_1.7b_ace15.safetensors`.
Configuration
The saved example uses a 120-second duration and fixed seed 31.
Cautions
The `qwen_1.7b_ace15.safetensors` file is a text encoder component, not a standalone audio generator.
Use that file with the matching workflow and its companion model files.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceVerified Oct 1
Source excerpts
2 excerpts
Source excerpts
2 excerpts--- license: apache-2.0 tags: - safetensors - text-encoder - dms-archive library_name: DMS public model archive --- # ACE-Step 1.5 Qwen 1.7B text encoder This repository contains one safetensors artifact from the Daniel Media Studio model archive. It is intentionally separated from the other archive entries so the file, provenance, license evidence, and usage notes are reviewable on one page. ## Artifact - File: 'qwen_1.7b_ace15.safetensors' - Size: 3708523360 bytes - SHA-256: 'ed63e9247d1f55f3ace04fa11e95b085fc82d459c82c5626f0b2e37b91ebd710' - Role: music generation text encoder component - Creator or upstream attribution: Comfy-Org repack; ACE-Step upstream ## How to use it This repository is an archive of the component, not a guaranteed standalone pipeline. Place the file in the model directory expected by the matching workflow, then load the recorded base model, VAE, tokenizer, ControlNet, or other companions. LoRA files must be attached to a compatible base pipeline; VAE and encoder files must be selected in the matching workflow; checkpoint shards must remain together with their index and companion shards. ### Required companions - acestep_v1.5_base.safetensors - acestep_v1.5_turbo.safetensors - ACE-Step VAE, codec, tokenizer, and workflow ### DMS note DMS integration is archive-only. Use the DMS workflow catalog and broker-controlled job path to select this artifact. Do not assume a component can generate media by itself. ## Provenance ### Source repositories - Comfy-Org/ace_step_1.5_ComfyUI_files ### Source URLs - https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_1.7b_ace15.safetensors - https://huggingface.co/ACE-Step/Ace-Step1.5 ## License and attribution Recorded license: Apache-2.0 repack plus upstream ACE-Step MIT terms. See LICENSE.txt and source/ for preserved evidence. The original-author material preserved under source/ is included for attribution and usage context. No new ownership claim is made over the upstream model, workflow, images, or documentation.
Source context: 0 downloads · 0 likes · Library DMS public model archive · Repo DanielMarius/qwen_1.7b_ace15.safetensors
