Image generation

What GPU do I need to run HiDream-ai/HiDream-I1-Full?

A 17.1B-parameter text-to-image model. 17.1B parameters, published in F16. View on Hugging Face

17.1B
Parameters
F16
Native precision
Not applicable
Context length
MIT
License
Image
Modality
HiDream
Organization

HiDream-I1-Full is published by HiDream-ai on Hugging Face, with 858 downloads and 1,000 likes to date. It's a unlisted-architecture model built for text-to-image, published natively in F16.

What HiDream-I1-Full is

HiDream-I1-Full is a 17.1B-parameter text-to-image model published by HiDream on Hugging Face, released under MIT.

License note: permissive: allows commercial use, modification and redistribution. Facts in this section are sourced from HiDream-I1-Full's Hugging Face model card, not benchmarked by Aquanode.

What it's used for

  • Text-to-image generation
  • Creative asset generation
  • ComfyUI workflows

VRAM required & cheapest live GPU fit

Required VRAM = weight size at each precision, plus a fixed overhead for activation memory and allocator fragmentation. Diffusion and video models carry no KV-cache. The real driver of extra memory is output resolution and frame count, which this flat overhead does not model. Full formula and assumptions: methodology.

PrecisionWeight sizeRequired VRAMCheapest live fitGPUs neededEst. $/hr (full fit)
FP1631.9 GB38.2 GBA1001$0.462/hr
cheaper alt.V1003$0.330/hr
FP8 (quantized)15.9 GB19.1 GBRTX 4000 Ada1$0.277/hr
INT4 (quantized)8.0 GB9.6 GBRTX 30601$0.125/hr

A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.

INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.

Cheapest way to run HiDream-I1-Full at its published (F16) precision: 1× A100, at $0.462/hr per GPU ($0.462/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.

HiDream-I1-Full: common questions

Can HiDream-I1-Full run on a single GPU?

Yes, but not on a desktop card. At FP16 it needs 38.2 GB of VRAM, more than a single 32 GB desktop card holds. The cheapest live single-card fit is a 40.0 GB A100 at $0.462/hr.

What is the least VRAM HiDream-I1-Full can run in?

9.6 GB, at INT4 (quantized), which fits a 12 GB card, against 38.2 GB at FP16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.

Does quantizing HiDream-I1-Full lower the GPU bill?

Yes. At FP16 the cheapest live fit is one A100 at $0.462/hr. At INT4 (quantized) it drops to one RTX 3060 at $0.125/hr, provided a quantized checkpoint exists for it.

How to run HiDream-I1-Full

Run HiDream-I1-Full with Diffusers (Python)

Generic example using Hugging Face's diffusers library, not from the model's own docs.

from diffusers import DiffusionPipeline
import torch

pipe = DiffusionPipeline.from_pretrained("HiDream-ai/HiDream-I1-Full", torch_dtype=torch.bfloat16)
pipe.to("cuda")
image = pipe("a description of the scene").images[0]
image.save("output.png")

Run HiDream-I1-Full with ComfyUI

Aquanode's ComfyUI template comes with ComfyUI preinstalled. Download HiDream-ai/HiDream-I1-Full's checkpoint into the models folder and load it in a workflow; this is a real Aquanode template, but loading this specific checkpoint is a manual step, not a one-click deploy.

Deploy HiDream-I1-Full on Aquanode

Aquanode has no one-click deploy template for HiDream-I1-Full; it comes with ComfyUI preinstalled, so you only need to load the checkpoint, not install anything. Aquanode sells GPU pods billed per second, not a hosted inference API.

  1. Launch the ComfyUI template sized to the requirement above (1× A100 or larger).
  2. Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
  3. Run the command and connect to the resulting endpoint.
Launch the ComfyUI template

Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.

More HiDream-ai models

All 2 HiDream-ai models: VRAM and GPU requirements

Alternatives at this size

Other models for text-to-image within about a third of HiDream-I1-Full's 17.1B parameters, from other model lines.

More on HiDream-I1-Full

Related reading: A100 pricing and specs, Fast diffusion inference on GPU VMs, and What AI inference is.

Related on Aquanode: All MiniCPM4 models and their GPU requirements. Browse the full lists: All HiDream-ai models and their GPU requirements.

ComfyUI on our compute

Rent a GPU with ComfyUI already installed. Your custom nodes and models are there next time.

$29 a month, or pay as you go

Start ComfyUI

Start ComfyUI on a rented GPU.

Sign up in 60 seconds. Pay for the GPU minutes you actually use.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.