Ace Step 1.5 XL Turbo and SFT - TEXT to AUDIO model with Ollama — v1.6 AceStep 1.5XL

Use this ComfyUI workflow to create Ace Step 1.5 songs from a song or artist reference, another description, or tags and lyrics you provide; it supports Turbo and SFT models, including XL variants, and can produce up to four songs.

Ollama can generate tags and lyrics, and you can also supply your own.

Generated audio can be saved as MP3.

For Ollama-generated tags, lyrics, or song titles, install Ollama, download a model, select it in Ollama Connectivity, and reconnect.

Place diffusion models, text encoders, and the Ace Step VAE in ComfyUI’s diffusion_models, text_encoders, and vae folders.

The listed model files are acestep_v1.5_turbo.safetensors, ace_1.5_vae.safetensors, qwen_0.6b_ace15.safetensors, and qwen_1.7b_ace15.safetensors.

The listed node packs are comfyui-easy-use 1.3.5, comfyui-ollama 2.1.0, and rgthree-comfy 1.0.2512112053.

For a first try, the author suggests starting with one Turbo or Turbo XL model before downloading more models.

Suggestion · not verified

This workflow is labeled v1.6, but its feature notes also mention v1.8; check the downloaded file’s version before relying on features described for later versions.

Suggestion · not verified