Text encoder
llama_3. 1_ 8b_ instruct_ fp8_ scaled. safetensors
Llama 3.1 8b Instruct FP8 scaled · Text encoder for ComfyUI
- File
llama_3.1_8b_instruct_fp8_scaled.safetensors- Type
- Text encoder
- Size
- 9.08 GB
- Folder
ComfyUI/models/text_encoders/- Source
- Comfy-Org/HiDream
- SHA-256
9f86897bbeb9…
5 workflows use this file
What is Llama 3.1 8b Instruct FP8 scaled?
Llama 3.1 8b Instruct 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 Llama 3.1 8b Instruct FP8 scaled with other models and custom nodes to build any pipeline you need. There are 5 official ComfyUI workflow templates that use Llama 3.1 8b Instruct FP8 scaled, ready to load and customize.
Read the full tutorial →Workflows for this file
- HiDream
HiDream E1.1 Image Editing
Uses this file - HiDream
HiDream E1 Image Edit
Uses this file - HiDream
HiDream I1 Dev
Uses this file - HiDream
HiDream I1 Full
Uses this file - HiDream
HiDream I1 Fast
Uses this file - Z-Image-Turbo
Z-Image-Turbo Text to Image
- Qwen-Image
Qwen Image Edit 2509
- Flux, Flux.2 Klein
Flux.2 [Klein] 4B Distilled: Image Edit
Frequently Asked Questions
Llama 3.1 8b Instruct 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 Llama 3.1 8b Instruct FP8 scaled with other models and custom nodes to build any pipeline you need. There are 5 official ComfyUI workflow templates that use Llama 3.1 8b Instruct FP8 scaled, ready to load and customize.
Follow the step-by-step tutorial at https://docs.comfy.org/tutorials/image/hidream/hidream-e1. You can also load any of the 5 official ComfyUI workflow templates that use Llama 3.1 8b Instruct FP8 scaled directly in ComfyUI.
There are 5 official ComfyUI workflow templates that use Llama 3.1 8b Instruct FP8 scaled. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Llama 3.1 8b Instruct 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.