Skip to main content

Deploy HiDream I1

Image

HiDream I1 is a 17B parameter image generation model with excellent prompt following. Available in Dev, Full, and Fast variants with FP8 quantization for efficient deployment on consumer GPUs.

Deploy HiDream I1 in minutes

Starting at $0.66/hr on dedicated GPU

Available Variants (3)

ModelGPUVRAMPriceAction
HiDream I1 Dev FP8
Dev FP8 (Recommended)
RTX A600048 GB$0.66/hrDeploy
HiDream I1 Full FP8
Full FP8
RTX A600048 GB$0.66/hrDeploy
HiDream I1 Fast FP8
Fast FP8 (4-step)
RTX A600048 GB$0.66/hrDeploy

Prices include 30% service fee. Billed per minute while running.

Requirements

HiDream I1 requires 48GB VRAM. Consumer GPUs like the RTX 5080 (16GB) or RTX 4090 (24GB) cannot run this model.

On ModelPilot, deploy on a dedicated cloud GPU (up to 80GB VRAM) starting at $0.66/hr with no setup required.

Includes full ComfyUI environment with custom node support.

Use Cases

  • Prompt-accurate image generation
  • Creative illustration
  • Commercial image production
  • Fine-tuning base model

Related Models

Frequently Asked Questions

How much VRAM does HiDream I1 need?

HiDream I1 requires 48GB VRAM.

How much does it cost to run HiDream I1?

Starting at $0.66/hr on a dedicated GPU. Billed per minute while running, with auto-stop when credits run out.

How long does HiDream I1 take to deploy?

Most deployments complete in 10–20 minutes including model download and environment setup.

Can I run HiDream I1 on my local GPU?

HiDream I1 requires 48GB+ VRAM, which exceeds most consumer GPUs. Cloud GPUs (A6000 48GB, A100 80GB) are recommended.

Ready to deploy HiDream I1?

Pick your GPU and have it running in minutes. No infrastructure setup required.