# HunyuanImage-2.1### An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation---## Performance on RTX 5090&gt; When using HunyuanImage-2.1 with the quantized encoder + quantized base model,&gt; the VRAM usage on an NVIDIA RTX 5090 typically ranges between 26 GB and 30 GB with average&gt; 16 second inference time depending on resolution, batch size, and prompt complexity.⚠ Important Note:The refiner and not yet implemented and are not ready for use in ComfyUI.Currently, only the base model and distilled is supported.[Example_Workflow](<a target="_blank" rel="ugc" href="https://huggingface.co/drbaph/HunyuanImage-2.1_fp8/resolve/main/example_workflow.json?download=true">https://huggingface.co/drbaph/HunyuanImage-2.1_fp8/resolve/main/example_workflow.json?download=true</a>)---### Workflow Notes- Model: HunyuanImage-2.1- Mode: Quantized Encoder + Quantized Base Model- VRAM Usage: ~26GB–30GB on RTX 5090- Resolution Tested: 2K (2048×2048)- Frameworks: ComfyUI &amp; Diffusers- Optimisations Works with Patch Sage Attention + Lazycache / TeaCache ✅- Refiner: ❌ Not implemented yet, not available in ComfyUI- License: [tencent-hunyuan-community](<a target="_blank" rel="ugc" href="https://github.com/Tencent-Hunyuan/HunyuanImage-2.1/blob/master/LICENSE">https://github.com/Tencent-Hunyuan/HunyuanImage-2.1/blob/master/LICENSE</a>)---

Files with SHA256: 696d62744686a4f95fd8de3aa8c9bf7424026678d7b58cf1c7fa349db6304472