HiDream-ai / text-to-image updated 1 year ago

HiDream-I1-Full

Name: HiDream-I1-Full
Author: HiDream-ai

HiDream-I1 is a new open-source image generative foundation model with 17B parameters that achieves state-of-the-art image generation quality within seconds.

Params

17.1 B

Context

—

Downloads 30d

18 K

Likes

997

Commercial use: allowed mit Not gated SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

18 K18 K

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	f16	47.2 GB	55.0 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Parameters: 17.1 B
Tensor type: F16
Licence: mit
First seen on the Hub: 2025-04-06
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Compare with

stable-diffusion-v1-5 1.6 M dreamshaper-7 895 K Flux2-Klein-9B-True-V2 792 K sd-turbo 722 K Realistic_Vision_V5.1_noVAE 485 K Qwen-Image-Lightning 438 K

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB