Diffusion model
omnigen2_fp16. safetensors
Omnigen2 FP16 · Diffusion model for ComfyUI
- File
omnigen2_fp16.safetensors- Type
- Diffusion model
- Size
- 7.93 GB
- Folder
ComfyUI/models/diffusion_models/- Source
- Comfy-Org/OmniGen-2
- SHA-256
60dbde451077…
2 workflows use this file
What is Omnigen2 FP16?
Omnigen2 FP16 is a diffusion model, the core network that turns your prompts into the output. 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 Omnigen2 FP16 with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use Omnigen2 FP16, ready to load and customize.
Read the full tutorial →Workflows for this file
- OmniGen
OmniGen2: Text to Image
Uses this file - OmniGen
OmniGen2 Image Edit
Uses this file - OmniGen
NetaYume Lumina Text to Image
- 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
- Flux, Flux.2 Dev
Flux.2 Dev: Image Edit
- Flux, Flux.2 Klein
Flux.2 [Klein] 9B: Image Edit
Frequently Asked Questions
Omnigen2 FP16 is a diffusion model, the core network that turns your prompts into the output. 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 Omnigen2 FP16 with other models and custom nodes to build any pipeline you need. There are 2 official ComfyUI workflow templates that use Omnigen2 FP16, ready to load and customize.
Follow the step-by-step tutorial at https://docs.comfy.org/tutorials/image/omnigen/omnigen2. You can also load any of the 2 official ComfyUI workflow templates that use Omnigen2 FP16 directly in ComfyUI.
There are 2 official ComfyUI workflow templates that use Omnigen2 FP16. Each template is ready to run in ComfyUI and can be customized to suit your project.
ComfyUI is free and open source. Omnigen2 FP16 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.