whatmodel.sh / image / HiDream-O1-Image
HiDream-O1-Image
↗ share
+ contribute
HiDream-O1-Image is an open-weights image model from HiDream, released May 2026. Its published size is 8B parameters. Licence: mit.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of HiDream-O1-Image, out of 197 with a score, then more from HiDream.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 58 |  Krea 2 Large | 59±3 | api $0.060/image | ||
| 59 |  Qwen-Image-Edit-2509 | 59±3 | api $0.030/image +local | ||
| 60 | HiDream-O1-Image | 58±2 | api $0.010/image +local | ||
| 61 |  FLUX.2 [dev] | 58±1 | api $0.046/image +local | ||
| 62 |  Reve V1 | 58±4 | comparison only | ||
| more from HiDream | |||||
| 86 | HiDream-O1-Image-Dev | 54±5 | comparison only | ||
| 116 | HiDream-I1-Full | 47±2 | api $0.050/image +local | ||
| 190 | HiDream-E1.1 | 26±11 | comparison only | ||
$ what it's good at
text to image▂▅▅▃▄▄█▃▁▂▁▁ #49 of 126 · 90% of its score · 7 tests
Beats Wan 2.7 Image here, though they rank higher overall. Trails Z-Image (Base), FLUX.2 [dev] here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena text-to-image | 1116.2 ✎ | ▂▂▃▄▇█▄▂▄▂·▂ beats 33/75 | 53% |
| QC-T2I-Bench (English, HCQ total) | 86.8% ✎ | ▄····▄█▄▄█▄█ beats 5/10 | 16% |
| UltraText Bench (Composite, bilingual dense text rendering) | 45.6% ✎ | ▁▂▂█▃▁▂▃·▁·▁ beats 11/22 | 15% |
| DPG-Bench lab | 89.8% ✎ | ▄·▂·▂▆█▄▂▄▂▃ beats 17/17 | 4.3% |
| LongText-Bench (EN) lab | 97.9% ✎ | ▃·····▅██▅▃▃ beats 12/12 | 1.9% |
| LongText-Bench (CN) lab | 97.8% ✎ | ▃·······████ beats 11/12 | 0.2% |
| GenEval lab | 90.0% ✎ | ▇▃▅▇▁▄▅▃█▃▃▅ beats 38/39 | — |
other tests1 not in a task · 8.3% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Rapidata Benchmark.ai image benchmark (overall Elo) | 988.2 ✎ | ▁▁▁▄▂█▂▁▁▂▁▁ beats 13/34 | 8.3% |
$ where to run it
Through an API
api · fal.ai · $0.010/image · fal.ai ↗ · price sourceUSD for one 1-megapixel output: fal bills this endpoint $0.01 per output megapixel (price = rate × 1 MP; fal's rounding for 1024×1024 ≈ 1.05 MP is not stated; larger outputs up to ~2K cost proportionally more). Product: fal.ai serverless text-to-image. API model: fal-ai/hidream-o1-image (full model: 50 denoising steps and guidance 5.0 by default; the separate /dev endpoint is not used). Settings: 1 MP output, one image. Price basis: published per-megapixel list rate × 1 MP. Currency: USD. Not a HiDream direct tariff. fal.ai official model page, observed 2026-09-25.
Other ways to run it
version
- Run it as published · needs ~19.7 GB, NVIDIA only · from huggingface.co/drbaph
git clone https://github.com/HiDream-ai/HiDream-O1-Image && cd HiDream-O1-Image && uvx --from huggingface_hub hf download HiDream-ai/HiDream-O1-Image --local-dir ckpt && uv run --with-requirements requirements.txt python inference.py --model_path ckpt --prompt "a cat holding a sign" --output_image out.png
Weights and documentation: huggingface.co/HiDream-ai ↗
$ how the score was worked out · LMArena leaderboard dataset 53%, QC-T2I-Bench: Scalable Questi… 16%, UltraText Bench: A Comprehens… 15% and 2 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 1 | 53% |
 QC-T2I-Bench: Scalable Question-Centric Text-to-Image Evaluation (Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing) | 1 | 16% |
| UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1) | 1 | 15% |
 Rapidata/text-to-image-human-preference-6M (Benchmark.ai Image Benchmark) published dataset-card rankings | 1 | 8% |
| HiDream-ai/HiDream-O1-Image repository README results · lab-reported | 3 | 6% |
| prior · pull toward the middle | 2% | |
| weighted average | = 58.4 |
not counted (1)
| HiDream-ai/HiDream-O1-Image repository README results | GenEval [correct] | 90.0% | fewer than three models have this test yet, or this source ran it for this model alone |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json