How to run HiDream-I1 Full locally

HiDream.ai · Text → image · 17B params · MIT (commercial OK)

A 17B MoE diffusion model with top open GenEval/DPG scores, fully MIT-licensed for unrestricted commercial use; Dev/Fast distilled variants also exist.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 16 GB of VRAM (NF4 ~16GB; full bf16 needs ~30GB+ or offload), via ComfyUI / Diffusers.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at HiDream-ai/HiDream-I1-Full.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → image
VRAM to run	~16 GB (NF4 ~16GB; full bf16 needs ~30GB+ or offload)
Download	~35 GB
Parameters	17B
License	MIT (commercial use OK)
Run with	ComfyUI / Diffusers

Get HiDream-I1 Full on Hugging Face →

More image models

FLUX.1 [dev] — Text → image, ~12 GB VRAM
Stable Diffusion XL 1.0 (SDXL) — Text → image, ~8.0 GB VRAM
Stable Diffusion 1.5 — Text → image, ~4.0 GB VRAM
FLUX.1 Kontext [dev] — Image editing, ~12 GB VRAM
FLUX.1 [schnell] — Text → image, ~12 GB VRAM
Qwen-Image — Text → image, ~24 GB VRAM

Browse: all media models · chat / LLM models