The most useful versions of GGUF(+the FP8 version)EDIT:*GGUF Workflow, since i can't upload the .json here: <a target="_blank" rel="ugc" href="https://www.kombitz.com/2025/04/17/simple-comfyui-workflow-for-hidream-i1-gguf/">https://www.kombitz.com/2025/04/17/simple-comfyui-workflow-for-hidream-i1-gguf/</a>*missing nodes? run Comfy update\update_comfyui.bat*quality comparison here: <a target="_blank" rel="ugc" href="https://artificialanalysis.ai/text-to-image/model-family/hidream#quality">https://artificialanalysis.ai/text-to-image/model-family/hidream#quality</a>Lighter versions of the Full HiDream quantized by <a target="_blank" rel="ugc" href="https://huggingface.co/city96">city96</a>download and use locally. nodes here:<a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF">https://github.com/city96/ComfyUI-GGUF</a>vae and text encoders here:<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/tree/main/split_files">https://huggingface.co/Comfy-Org/HiDream-I1_ComfyUI/tree/main/split_files</a>

HiDream-Full   GGUF+FP8+WORKFLOW (Q4 for 12GB Q2 for 8GB)

Files with SHA256: 093486b1761400c895f4c5966eea26be26495505154a8a5b6ef3d5c66f23e022