---
source: 'https://howaiworks.ai/models/hidream'
section: models
title: HiDream-O1-Image
description: >-
  HiDream.ai's 8B pixel-level unified transformer, open-sourced under MIT on May
  8, 2026. No VAE, no separate text encoder, and generates up to 2,048x2,048.
tags:
  - HiDream
  - HiDream.ai
  - Image Generation
  - Text-to-Image
  - Image Editing
  - Unified Transformer
  - Open Source
  - MIT License
  - Chinese AI
  - Latest
category: Image Generation Models
developer: HiDream.ai
developerWebsite: 'https://hidreamai.com/'
modelType: Image Generation Model
releaseDate: '2026-05-08'
lastUpdated: '2026-07-08'
license: MIT
officialWebsite: 'https://hidream.ai/'
docsPage: 'https://github.com/HiDream-ai/HiDream-O1-Image'
---

# HiDream-O1-Image

> HiDream.ai's 8B pixel-level unified transformer, open-sourced under MIT on May 8, 2026. No VAE, no separate text encoder, and generates up to 2,048x2,048.

## Overview

**HiDream-O1-Image** is an [image generation](https://howaiworks.ai/glossary/image-generation) foundation model from HiDream.ai, **released on May 8, 2026** under the MIT License. Its Hugging Face repository was created at `2026-05-08T13:06:04Z`, and the model card's Project Updates log records: *"May 8, 2026: We've open-sourced HiDream-O1-Image (8B), including both the undistilled and distilled Dev variants, together with the Reasoning-Driven Prompt Agent."*

The architecture is the reason to care. HiDream describes it in one line — *"One end-to-end model on raw pixels, no VAE, no disjoint text encoder"* — and the [arXiv abstract](https://arxiv.org/abs/2605.11061) restates it: the Pixel-level Unified [Transformer](https://howaiworks.ai/glossary/transformer) (UiT) works by *"mapping raw image pixels, text tokens, and task-specific conditions into a single shared token space"*, which *"eliminates the need for separate VAEs or disjoint pre-trained text encoders."* Practically every rival — [Stable Diffusion](https://howaiworks.ai/models/stable-diffusion), FLUX, [Qwen-Image](https://howaiworks.ai/models/qwen-image), [Z-Image](https://howaiworks.ai/models/z-image) — is a *latent* diffusion model: an [autoencoder](https://howaiworks.ai/glossary/autoencoder) compresses the image roughly 8x per side, the transformer denoises in that latent space, and a decoder reconstructs pixels. HiDream deletes both halves of the autoencoder and one whole text encoder, and pushes the transformer down onto raw pixels.

The results are strong and the distribution is small. On **Artificial Analysis's text-to-image arena**, the closed **HiDream-O1-Image-1.5** sits at **#4 of 149 ranked models** with an Elo of **1,265** — the highest-placed model from any Chinese developer, ahead of OpenAI's GPT Image 1.5 (high). The open, MIT-licensed **HiDream-O1-Image-Dev-2604** is **#2 among open-weights models**. And yet `HiDream-ai/HiDream-O1-Image` has **22,788 Hugging Face downloads in the trailing 30 days**, against 933,580 for Alibaba's Z-Image-Turbo — a model 8 arena places *below* it on that same board (#69 against #61). **The #4 result belongs to the checkpoint you cannot download; the checkpoint you can download sits at #61.** Downloads measure size, licence friction, and tooling support; they do not measure quality.

HiDream.ai (**北京智象未来科技有限公司**, Beijing Zhixiang Future Technology) is a Chinese startup founded in **March 2023**, whose stated mission is *"to provide responsible intelligence for a better future."* Its founder and CEO is **Dr. Tao Mei** (the corporate site renders his name *Dr. Mei Tao*). His prior roles at JD.com and Microsoft Research are widely reported elsewhere but appear nowhere on HiDream's own site, so this page does not assert them.

### A note on naming

The HiDream O1 family has an open tier and a closed tier, and the names do not warn you which is which.

**MIT, open weights, downloadable today:**

| Repository | Steps | Released | Downloads (30d) |
|---|---|---|---|
| `HiDream-ai/HiDream-O1-Image` | 50 | 2026-05-08 | 22,788 |
| `HiDream-ai/HiDream-O1-Image-Dev` | 28 | 2026-05-08 | 1,636 |
| `HiDream-ai/HiDream-O1-Image-Dev-2604` | 28 | 2026-05-14 | 1,597 |

**Closed. No weights, anywhere:**

- **HiDream-O1-Image-1.5** — the current flagship. hidream.ai's hero headline reads *"HiDream O1 Image 1.5"* over the strapline *"Natively unified. The latest flagship."* The `HiDream-ai` Hugging Face organisation contains fourteen repositories and **none is named 1.5**; the API returns `401` for `HiDream-ai/HiDream-O1-Image-1.5` (though a repo id that has never existed also returns `401`, so that signal alone proves nothing). Artificial Analysis stores `openWeightsUrl: null` against its 1.5 row while linking real Hugging Face URLs for the 8B variants. AA's own note on the row: *"HiDream-O1-Image-1.5 is the latest version of HiDream O1. Earlier variants, including HiDream-O1-Image, HiDream-O1-Image-Dev, and HiDream-O1-Image-Dev-2604, are benchmarked and listed separately."*
- **HiDream-O1-Image-Pro (200B+)** — appears as the top row of every benchmark table in HiDream's own model card and technical report. No weights, no repository, no arena entry. **HiDream publishes no statement equating Pro with 1.5, so this page does not equate them.**

**HiDream-O1-Image is not HiDream-I1.** `HiDream-I1-Full` / `-Dev` / `-Fast` are the April 2025 latent-diffusion generation. They are also MIT, `HiDream-I1-Fast` is still the org's most-downloaded model (51,789 downloads/30d, more than twice the new flagship), and they are a different architecture entirely.

## Capabilities

- **One model, many tasks.** Text-to-image, instruction-based image editing, subject-driven personalization from multiple references, long-text rendering, layout and skeleton conditioning, and storyboard generation — all from a single set of weights, with no task-specific adapters.
- **No VAE, no text encoder.** The UiT natively ingests raw pixels, text tokens and task conditions in one token stream. Nothing is compressed into a latent space and nothing is embedded by a frozen external encoder.
- **Native 2,048 x 2,048 synthesis.** HiDream calls this *"Direct synthesis up to 2,048 × 2,048 with sharp fine-grained detail"* — not an upscale pass.
- **Reasoning-Driven Prompt Agent.** A separate *"thinking" agent* (see [chain-of-thought](https://howaiworks.ai/glossary/chain-of-thought)) that *"explicitly reasons through layout, subject attributes, physical logic, and text-rendering details, then rewrites a raw user instruction into a self-contained English prompt."* It is a distinct 31B model, not part of the 8B.
- **Bilingual long-text rendering.** HiDream reports 0.979 (EN) and 0.978 (ZH) on LongText-Bench for the 8B. In HiDream's own table the 8B places second on ZH but third on EN, behind Nano Banana 2.0 (0.980) as well as HiDream's unreleased Pro.
- **Two sampling budgets.** The full model runs 50 [inference](https://howaiworks.ai/glossary/inference) steps; the Dev variants run 28, via [distillation](https://howaiworks.ai/glossary/knowledge-distillation).

## Technical Specifications

- **Hugging Face repositories**: `HiDream-ai/HiDream-O1-Image`, `HiDream-ai/HiDream-O1-Image-Dev`, `HiDream-ai/HiDream-O1-Image-Dev-2604`
- **Parameters**: `total_parameters: 8,804,887,792` (8.80B) per the checkpoint's `model.safetensors.index.json` — the whole model, encoder included. Dev-2604 reports an identical count.
- **Architecture**: Pixel-level Unified Transformer (UiT). The `config.json` declares `"architectures": ["Qwen3VLForConditionalGeneration"]` and `"model_type": "qwen3_vl"`; text tower 4,096 hidden / 36 layers / 32 [attention](https://howaiworks.ai/glossary/attention-mechanism) heads / 8 KV heads, vision tower depth 27, patch size 16. HiDream's documentation does not discuss this lineage.
- **VAE**: none. This is the defining property of the model.
- **Precision / disk**: FP32 weights, `total_size: 35,219,551,168` bytes (35.22 GB) across 8 safetensors shards
- **Resolution**: up to 2,048 x 2,048
- **Sampling steps**: 50 (full), 28 (Dev, Dev-2604)
- **Prompt agent**: `google/gemma-4-31B-it` for the base model; `HiDream-ai/Prompt-Refine` (a Gemma-4-31B-it finetune, MIT) for Dev-2604
- **Attention kernel**: `flash-attn` strongly recommended; without it you must edit `models/pipeline.py` line 341 or inference fails
- **License**: MIT — on all three repositories and on the GitHub repo
- **Paper**: [arXiv:2605.11061](https://arxiv.org/abs/2605.11061), submitted May 11, 2026
- **HiDream does not publish a VRAM requirement, a training compute figure, or a training-data description**, so this page states none.

## Use Cases

- **Poster, packaging and signage design with heavy embedded text** — HiDream self-reports 0.979 (EN) and 0.978 (ZH) on the LongText-Bench [benchmark](https://howaiworks.ai/glossary/benchmark), within 0.001 of the best score in its own table.
- **Editing and generation in one deployment** — one checkpoint replaces a separate text-to-image model, an editing model, and an IP-adapter stack.
- **Subject-driven personalization** — preserving a character or product identity across new scenes from multiple reference images.
- **Storyboarding and layout-conditioned generation** — the May 13, 2026 update added layout and skeleton conditioning to the IP pipeline.
- **Pixel-space generation research** — the only competitive, permissively licensed, VAE-free image model to study. Latent-space artefacts simply do not exist here.
- **Commercially unconstrained products** — MIT has no revenue cap, unlike [Stable Diffusion 3.5](https://howaiworks.ai/models/stable-diffusion)'s $1M Community License threshold.

## Performance / Benchmarks

**arena.ai** (the former LMArena) and **Artificial Analysis** are different organisations running different Elo scales. Their numbers are never comparable to each other.

### Artificial Analysis text-to-image arena (fetched 2026-07-08; 149 ranked models, 133 marked current)

| Rank | Model | Creator | Elo | Appearances | Open weights |
|---|---|---|---|---|---|
| 1 | GPT Image 2 (high) | OpenAI | 1,339 | 13,374 | No |
| 2 | Reve 2.0 | Reve | 1,281 | — | No |
| 3 | MAI-Image-2.5 | Microsoft AI | 1,271 | 5,354 | No |
| **4** | **HiDream-O1-Image-1.5** | **HiDream** | **1,265** | **6,292** | **No** |
| 5 | GPT Image 1.5 (high) | OpenAI | 1,260 | 8,486 | No |
| 8 | Cosmos3-Super-Text2Image (agentic) | NVIDIA | 1,226 | 5,855 | **Yes** |
| **20** | **HiDream-O1-Image-Dev-2604** | **HiDream** | **1,187** | **5,885** | **Yes** |
| 28 | ERNIE Image | Baidu | 1,168 | 3,649 | Yes |
| 47 | Vivago 2.1 | HiDream | 1,135 | 5,525 | No |
| 61 | HiDream-O1-Image | HiDream | 1,111 | 4,864 | Yes |
| 69 | Z-Image Turbo | Alibaba | 1,104 | 7,884 | Yes |
| 76 | HiDream-O1-Image-Dev | HiDream | 1,088 | 4,791 | Yes |

Three observations, all uncomfortable for someone:

1. **HiDream-O1-Image-1.5 is the highest-ranked Chinese image model on this board**, at #4, with a 69% win rate and a 95% confidence interval of 1,256–1,274. Ranks 1, 2, 3 and 5 are OpenAI, Reve, Microsoft AI and OpenAI. **It is closed.**
2. **The open Dev-2604 outranks the open full model by 76 Elo** — #20 versus #61. The 28-step distilled checkpoint paired with a prompt refiner beats the 50-step undistilled one. HiDream's model card does not explain this.
3. **Dev-2604 is #2 open-weights, not #1.** AA's own FAQ: *"Cosmos3-Super-Text2Image (agentic) currently leads among open weights models in the Artificial Analysis Text to Image Arena with an Elo score of 1226, followed by HiDream-O1-Image-Dev-2604 (Elo 1187) and ERNIE Image (Elo 1168)."*

### The vendor's stale banner

HiDream's model card still leads with: *"HiDream-O1-Image-Dev-2604 debuts at #8 in the Artificial Analysis Text to Image Arena, which is positioned to be the new leading open weights Text to Image model."* That claim dates to mid-May 2026 and **is no longer true**. NVIDIA's Cosmos3-Super-Text2Image shipped 2026-05-31 (AA's recorded release date) and now holds both the #8 slot and the open-weights lead. Dev-2604 has slipped to #20.

### arena.ai text-to-image leaderboard (fetched 2026-07-08; 72 models)

| Rank | Model | Org | Elo | Votes | License |
|---|---|---|---|---|---|
| 1 | gpt-image-2 (medium) | OpenAI | 1385.04 | 58,643 | Proprietary |
| 33 | qwen-image-2512 | Alibaba | 1126.86 | 82,460 | Apache 2.0 |
| **34** | **hidream-o1-image** | **HiDream** | **1120.86** | **23,109** | **MIT** |
| 48 | z-image-turbo | Alibaba | 1080.92 | 19,719 | Apache 2.0 |

Only the *full open* checkpoint is ranked here, at **#34 of 72**. `hidream-o1-image-1.5` is registered as a votable model in arena.ai's roster but carries **no leaderboard rank**, so arena.ai offers no independent read on the flagship.

### Vendor-reported benchmarks (HiDream's own model card — treat as vendor claims)

| Benchmark | HiDream-O1-Image (8B) | HiDream-O1-Image-Pro (200B+) | Best competitor listed |
|---|---|---|---|
| GenEval (overall) | 0.90 | **0.92** | GPT Image 2 — 0.89 |
| DPG-Bench (overall) | 89.83 | **90.30** | Seedream-4.0 — 88.63 |
| HPSv3 (all) | 10.37 | **10.47** | GPT Image 2 — 10.21 |
| CVTG-2K (average) | 0.9128 | **0.9222** | Seedream-4.0 / GPT Image 2 — 0.9003 |
| LongText-Bench EN / ZH | 0.979 / 0.978 | **0.982 / 0.980** | Nano Banana 2.0 — 0.980 / 0.965 |

In all five tables HiDream awards first place to its own unreleased Pro model, and in four of the five it awards second place to its own 8B — the exception is LongText-Bench-EN, where Nano Banana 2.0 (0.980) edges the 8B (0.979). HiDream summarises: *"With only 8B parameters, achieves performance parity with or even surpasses larger open-source DiTs and leading closed-source models."* These are self-run evaluations, published without third-party replication.

## Limitations

- **The flagship is closed.** The #4 arena result belongs to HiDream-O1-Image-1.5, which you cannot download, inspect, or self-host. The MIT weights you *can* download rank #20 (Dev-2604) and #61 (full) on the same board.
- **HiDream-O1-Image-Pro may not be a product at all.** It is a 200B+ column in HiDream's own tables with no weights, no API listing, and no arena presence. Every "beats GPT Image 2" headline traceable to it is a claim about a model no one outside HiDream has used.
- **"8B" excludes a 31B prompt agent.** The Reasoning-Driven Prompt Agent runs `google/gemma-4-31B-it`, and Dev-2604's recommended pipeline runs `HiDream-ai/Prompt-Refine`, a Gemma-4-31B-it finetune. The leaderboard-winning configuration is roughly 40B of weights, not 8B.
- **Every quality number in the model card is a vendor claim.** HiDream ran all five benchmark suites itself and takes first place in every one, and second place in four of the five. Both independent arenas rank the open checkpoints far lower than the tables imply.
- **The model card's headline claim is stale.** "the new leading open weights Text to Image model" has been false since NVIDIA's Cosmos3-Super-Text2Image landed on 2026-05-31.
- **35.22 GB of FP32 weights, and no published VRAM figure.** HiDream states no memory requirement, and ships no quantised release. `flash-attn` is effectively mandatory. There is no consumer-GPU story comparable to [Z-Image](https://howaiworks.ai/models/z-image)'s.
- **Essentially no ecosystem.** 1,203 GitHub stars against Z-Image's roughly 11,700; the `diffusers` pipeline PR (#13749) is still unmerged; no Hugging Face inference provider is mapped; 3,257 all-time downloads for Dev-2604. Inference requires HiDream's own repository or a hosted endpoint at WaveSpeed or fal.ai.
- **Nothing is disclosed about training.** No dataset description, no compute budget, no data-provenance statement.
- **Last commit June 22, 2026** — and the only update that day was a Discord link.

## Pricing & Access

### Self-hosting

**Free, under a real open-source licence.** MIT on `HiDream-O1-Image`, `HiDream-O1-Image-Dev`, `HiDream-O1-Image-Dev-2604`, `Prompt-Refine`, and on the GitHub repository (confirmed via the GitHub API: `"spdx_id": "MIT"`). No revenue cap, no field-of-use restriction, no geographic exclusion. Training data is not released, so this is open weights *plus* an open licence — not open data.

### Hosted access

**HiDream publishes no rate card we could verify.** hidream.ai displays no pricing. Hugging Face's `inferenceProviderMapping` is **empty** for both `HiDream-O1-Image` and `HiDream-O1-Image-Dev-2604` — no HF-routed provider serves them.

| Source | Figure | Notes |
|---|---|---|
| Artificial Analysis | **$80.00 / 1,000 images** ($0.08/image) for HiDream-O1-Image-1.5 | AA's own collected price, not a HiDream rate card |
| Artificial Analysis | Third-party hosts: **WaveSpeed** ($10/1k) and **fal.ai** ($40/1k) for O1-Image; **WaveSpeed** ($5/1k) and **fal.ai** ($20/1k) for O1-Image-Dev; **Replicate**, **Runware**, **WaveSpeed** and **fal.ai** for HiDream-I1-Dev; **Runware** and **Vivago AI** for HiDream-I1-Fast | AA lists no endpoint at all for Dev-2604 or 1.5. Only Vivago is HiDream's own |

Free demos run on Hugging Face Spaces: `HiDream-ai/HiDream-O1-Image` (139 likes), `HiDream-ai/HiDream-O1-Image-Dev`, `HiDream-ai/HiDream-O1-Image-Dev-2604`.

### HiDream's consumer product

**Vivago.ai is real and it is HiDream's.** The `HiDream-ai` GitHub organisation lists `https://vivago.ai/` as its website, hidreamai.com links out to vivago.ai, and Artificial Analysis benchmarks **Vivago 2.1** (#47, Elo 1,135, released 2025-10-20) and **Vivago 2.0** (#63, Elo 1,108, released 2025-06-10) with the creator field set to *HiDream*. AA also lists a `vivago_hidream-i1-fast` endpoint. HiDream's own product pages name Pixeling, PixMaker and HiHarness. We have verified none of Vivago's own product claims, so this page states nothing about its features, user numbers, pricing, or funding.

## Ecosystem & Tools

- **[github.com/HiDream-ai/HiDream-O1-Image](https://github.com/HiDream-ai/HiDream-O1-Image)** — HiDream's only supported self-hosting path. 1,203 stars, 33 forks, MIT, last pushed 2026-06-22. `inference.py` (main) for the full model, `dev` branch for Dev-2604.
- **`app.py`** — a single-file Flask web UI shipped in the repo, exposing every generation mode plus the Prompt Agent, on port 7860.
- **[HiDream-ai/Prompt-Refine](https://huggingface.co/HiDream-ai/Prompt-Refine)** — the Gemma-4-31B-it finetune that Dev-2604's [prompt-engineering](https://howaiworks.ai/glossary/prompt-engineering) pipeline depends on. MIT.
- **[Hugging Face Spaces](https://huggingface.co/spaces/HiDream-ai/HiDream-O1-Image)** — official hosted demos for all three open checkpoints.
- **WaveSpeed and fal.ai** — the two third-party hosts Artificial Analysis lists for the O1 generation, each serving `HiDream-O1-Image` and `HiDream-O1-Image-Dev`. AA lists no endpoint for Dev-2604 or 1.5.
- **[diffusers PR #13749](https://github.com/huggingface/diffusers/pull/13749)** — *"feat: Add HiDream-O1 transformer and image generation pipeline"*, still **open** as of July 8, 2026. Until it merges there is no `diffusers` path; the checkpoint loads through `transformers` plus HiDream's own `models/pipeline.py`.
- **ComfyUI, ModelScope** — linked as ecosystem targets from hidream.ai.
- **[Discord](https://discord.gg/7ZEnPxdTQ)** — opened June 22, 2026.

## Community & Resources

- [HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer](https://arxiv.org/abs/2605.11061) — the technical report (submitted 2026-05-11); source of the UiT and no-VAE claims
- [HiDream-ai/HiDream-O1-Image on Hugging Face](https://huggingface.co/HiDream-ai/HiDream-O1-Image) — 8.80B FP32 weights, MIT, the Project Updates log, all five benchmark tables
- [HiDream-ai/HiDream-O1-Image-Dev-2604 on Hugging Face](https://huggingface.co/HiDream-ai/HiDream-O1-Image-Dev-2604) — the 28-step checkpoint that AA ranks #2 open-weights
- [HiDream-ai/HiDream-O1-Image on GitHub](https://github.com/HiDream-ai/HiDream-O1-Image) — code, MIT LICENSE, `dev` branch
- [hidream.ai](https://hidream.ai/) — the project landing page, where HiDream O1 Image 1.5 is called "the latest flagship"
- [hidreamai.com](https://hidreamai.com/home/about) — the corporate site: 北京智象未来科技有限公司, founded March 2023
- [Artificial Analysis text-to-image arena](https://artificialanalysis.ai/image/leaderboard/text-to-image) — where 1.5 is #4 and Dev-2604 is #20
- [arena.ai text-to-image leaderboard](https://arena.ai/leaderboard/text-to-image) — where `hidream-o1-image` is #34 of 72
- Compare with [Z-Image](https://howaiworks.ai/models/z-image), [Qwen-Image 2.0](https://howaiworks.ai/models/qwen-image), [HunyuanImage 3.0](https://howaiworks.ai/models/hunyuan-image), [Seedream 5.0](https://howaiworks.ai/models/seedream), and [Stable Diffusion 3.5](https://howaiworks.ai/models/stable-diffusion)

## Frequently Asked Questions

### When was HiDream-O1-Image released?

May 8, 2026. The model card's Project Updates log reads "May 8, 2026: We've open-sourced HiDream-O1-Image (8B)", and the Hugging Face repository was created at 2026-05-08T13:06:04Z. The technical report followed on May 10 and HiDream-O1-Image-Dev-2604 on May 14, 2026.

### Is HiDream-O1-Image open source?

Yes, genuinely. `HiDream-ai/HiDream-O1-Image`, `HiDream-O1-Image-Dev` and `HiDream-O1-Image-Dev-2604` all carry the `license:mit` tag on Hugging Face, the GitHub repository is MIT per the GitHub API, and the model card states "The code in this repository and the HiDream-O1-Image models are licensed under MIT License." There are no field-of-use or geographic restrictions. Training data is not released.

### Is HiDream-O1-Image-1.5 open source?

No. It is the flagship, and it is closed. No `HiDream-O1-Image-1.5` repository exists in the `HiDream-ai` Hugging Face organisation (14 repositories, none named 1.5), and Artificial Analysis records `openWeightsUrl: null` against its 1.5 row while linking real Hugging Face URLs for the 8B variants. Do not conflate the two.

### What is a Pixel-level Unified Transformer, and why does it matter?

It is a single transformer that operates directly on raw image pixels. HiDream's model card describes "One end-to-end model on raw pixels, no VAE, no disjoint text encoder," and the arXiv abstract says the design "eliminates the need for separate VAEs or disjoint pre-trained text encoders." Nearly every competing image model — Stable Diffusion, FLUX, Qwen-Image, Z-Image — is a latent diffusion model that encodes images into a compressed VAE latent space first.

### How does HiDream rank against other image models?

On Artificial Analysis's text-to-image arena (fetched July 8, 2026), the closed HiDream-O1-Image-1.5 is #4 of 149 ranked models with an Elo of 1,265 — above GPT Image 1.5 (high) — and is the highest-placed model from a Chinese developer. The open HiDream-O1-Image-Dev-2604 is #20 overall and #2 among open-weights models, behind NVIDIA's Cosmos3-Super-Text2Image (agentic).

### Wasn't HiDream-O1-Image-Dev-2604 the leading open-weights model?

Briefly. The model card still carries the banner "HiDream-O1-Image-Dev-2604 debuts at #8 in the Artificial Analysis Text to Image Arena, which is positioned to be the new leading open weights Text to Image model." That was written in May 2026. Artificial Analysis's own FAQ now states that "Cosmos3-Super-Text2Image (agentic) currently leads among open weights models... with an Elo score of 1226, followed by HiDream-O1-Image-Dev-2604 (Elo 1187)." NVIDIA's model shipped on 2026-05-31, after the banner was written.

### Does HiDream-O1-Image really have only 8B parameters?

The checkpoint's `model.safetensors.index.json` reports `total_parameters: 8,804,887,792` — 8.80B, in FP32, 35.22 GB on disk. Unusually, that figure covers the whole model: there is no separate text encoder to add. Competitors in HiDream's own comparison tables are listed as sums (Qwen-Image "7B + 20B", FLUX.2 [Dev] "24B + 32B"). The caveat is that the recommended prompt pipeline calls a 31B Gemma model that is not counted.

### How much does HiDream-O1-Image cost?

Self-hosting is free under MIT. HiDream publishes no rate card that we could verify — hidream.ai displays no pricing. Artificial Analysis records an API price of $80.00 per 1,000 images ($0.08 per image) for HiDream-O1-Image-1.5. Hugging Face's `inferenceProviderMapping` is empty for both O1 repositories, so no HF-routed provider serves them.

### Who makes HiDream-O1-Image?

HiDream.ai (北京智象未来科技有限公司, Beijing Zhixiang Future Technology), a Chinese startup founded in March 2023 and led by founder and CEO Dr. Tao Mei, whose name the corporate site renders as Dr. Mei Tao. His widely reported prior roles at JD.com and Microsoft Research are not stated on HiDream's own site. The company also ships the consumer creation product Vivago.ai.

### Is HiDream-O1-Image widely used?

No. Hugging Face reports 22,788 downloads in the trailing 30 days and 55,278 all-time for `HiDream-ai/HiDream-O1-Image`. Alibaba's Apache-2.0 `Tongyi-MAI/Z-Image-Turbo` pulls 933,580 in the same window — roughly 41x more — while ranking eight places lower on Artificial Analysis's board (#69 against #61). Quality and adoption are decoupled here.

## Related

### Related models

- [Z-Image](https://howaiworks.ai/models/z-image)
- [Qwen-Image 3.0](https://howaiworks.ai/models/qwen-image)
- [HunyuanImage 3.0](https://howaiworks.ai/models/hunyuan-image)
- [Seedream 5.0](https://howaiworks.ai/models/seedream)
- [Stable Diffusion 3.5](https://howaiworks.ai/models/stable-diffusion)

---

Source: https://howaiworks.ai/models/hidream — HowAIWorks.ai