Text encoder
qwen3vl_4b_ fp8_ scaled. safetensors
Qwen3vl 4b FP8 scaled · Text encoder for ComfyUI
- File
qwen3vl_4b_fp8_scaled.safetensors- Type
- Text encoder
- Size
- 5.24 GB
- Folder
ComfyUI/models/text_encoders/- Source
- Comfy-Org/Krea-2
- SHA-256
54bd5144df0b…- Also published as
qwen3vl_4b_bf16.safetensors
4 workflows use this file
What is Qwen3vl 4b FP8 scaled?
Qwen3vl 4b FP8 scaled 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 Qwen3vl 4b FP8 scaled with other models and custom nodes to build any pipeline you need. There are 4 official ComfyUI workflow templates that use Qwen3vl 4b FP8 scaled, ready to load and customize.
Workflows for this file
- Qwen 3.0
Qwen3.0: Text Generation
- Z-Image-Turbo
Z-Image-Turbo Text to Image
- Flux, Flux.2 Klein
Flux.2 [Klein] 4B Distilled: Image Edit
- Flux, Flux.2 Dev
Flux.2 Dev: Image Edit
- Flux, Flux.2 Klein
Flux.2 [Klein] 9B: Image Edit
- Flux, Flux.2 Dev
Flux.2 Dev Text to Image
- Z-Image
Z-Image: Text to Image
- Z-Image-Turbo
Z-Image-Turbo Fun Union ControlNet
Frequently Asked Questions
Qwen3vl 4b FP8 scaled 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 Qwen3vl 4b FP8 scaled with other models and custom nodes to build any pipeline you need. There are 4 official ComfyUI workflow templates that use Qwen3vl 4b FP8 scaled, ready to load and customize.
Open ComfyUI and browse any of the 4 official ComfyUI workflow templates that use Qwen3vl 4b FP8 scaled. Load one as a starting point, then customize the nodes and parameters to fit your use case.
There are 4 official ComfyUI workflow templates that use Qwen3vl 4b FP8 scaled. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Qwen3vl 4b FP8 scaled 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.