Text encoder
qwen3.5_ 2b_ bf16. safetensors
Qwen3.5 2b BF16 · Text encoder for ComfyUI
- File
qwen3.5_2b_bf16.safetensors- Type
- Text encoder
- Size
- 4.55 GB
- Folder
ComfyUI/models/text_encoders/- Source
- Comfy-Org/Qwen3.5
- SHA-256
aa33250c4fc6…
2 workflows use this file
What is Qwen3.5 2b BF16?
Qwen3.5 2b BF16 is a text encoder that converts prompts into embeddings used to guide generation. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Qwen3.5 2b BF16 with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use Qwen3.5 2b BF16, ready to load and customize.
Workflows for this file
- Stable Audio, Stability
Stable Audio 1.0: Text to Audio
- ACE-Step
ACE-Step 1.5 Music Generation AIO
- Chatter Box
Chatter Box: Multilingual Text-to-Speech with Voice Cloning
- ACE-Step
ACE-Step 1.5 Music Generation Workflow
- ACE-Step
ACE-Step 1.5 Music Generation (4B LLM )
- ACE-Step
ACE-Step v1 Text to Instrumentals Music
- ACE-Step
ACE Step v1 Text to Song
Frequently Asked Questions
Qwen3.5 2b BF16 is a text encoder that converts prompts into embeddings used to guide generation. You can run it locally in ComfyUI with full control over every parameter, or access it through Comfy Cloud. ComfyUI's node-based workflow editor lets you connect Qwen3.5 2b BF16 with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use Qwen3.5 2b BF16, ready to load and customize.
Open ComfyUI and browse any of the 2 official ComfyUI workflow templates that use Qwen3.5 2b BF16. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There are 2 official ComfyUI workflow templates that use Qwen3.5 2b BF16. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Qwen3.5 2b BF16 weights are available to download from Hugging Face. You only pay for compute when running on Comfy Cloud; local inference on your own hardware is always free.