whatmodel.sh / image / Openjourney
Openjourney
↗ share
+ contribute
Openjourney is an open-weights image model from PromptHero, released November 2022. Its published size is 0.86B parameters. Licence: creativeml-openrail-m.
Catalogue identity notes
prompthero/openjourney (v1; Stable Diffusion 1.5 fine-tune on Midjourney images), not openjourney-v4. No parameter count published; memory estimated as for SD 1.x (0.86B UNet).
Model information sources
UNet only: OUR COUNT from the safetensors header of the repo's unet/diffusion_pytorch_model.safetensors (859,520,964, the Stable Diffusion v1 UNet size). The HF API safetensors total for this repo (123,060,557) is the root model.safetensors text-encoder copy, so it is not used. The single-file mdjrny-v4.safetensors (UNet + text encoder + VAE) has 1,066,235,384. Observed 2026-10-07.
Score within the LMArena text-to-image comparison set only.
$ how it compares
The image models ranked either side of Openjourney, out of 197 with a score.
| # | model | score | where |
|---|---|---|---|
| 183 |  DALL·E Mega (minDALL-E) | 29±4 | local |
| 184 |  MagicBrush (InstructPix2Pix fine-tune, jul7) | 29±7 | comparison only |
| 185 | Openjourney | 28±2 | local |
| 186 |  Stable Diffusion v1.4 | 27±2 | local |
| 187 | Stable Diffusion v1.3 | 27±4 | local |
$ what it's good at
text to image▃▅▅▃▄▄█▃▁▂▁▁ #120 of 126 · 55% of its score · 3 tests
Trails CogView2 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GenAI-Arena text-to-image (Elo, 4 Jun 2024) | 853.0 ✎ | ▃▃··▃·▃·█·▃▃ beats 1/8 | 38% |
| ImagenHub text-guided generation (human overall) | 50.0% ✎ | ▄▄·█·······▄ beats 0/4 | 16% |
| HPS v2 benchmark (4-style average) | 27.5% ✎ | ▃··▃▅·▅·▅▅█▅ beats 12/14 | 0.1% |
other tests2 not in a task · 43% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| EvalAlign human text-image alignment score | 4.8300 mean human alignment score ✎ | █▄▄·█·▄█▄▄·▄ beats 5/11 | 33% |
| HEIM text-image alignment (aspect win rate, v1.1.0) | 61.7% ✎ | ▁····█▁·▁··▁ beats 6/9 | 11% |
$ where to run it
Other ways to run it
version
- Run it as published · needs ~2.6 GB, NVIDIA only · from huggingface.co/prompthero (official)
uv run --with diffusers --with transformers --with accelerate --with torch python -c "import torch; from diffusers import StableDiffusionPipeline; p=StableDiffusionPipeline.from_pretrained('prompthero/openjourney', torch_dtype=torch.float16).to('cuda'); p('a cat holding a sign').images[0].save('out.png')"
Official weights and documentation: huggingface.co/prompthero ↗
$ how the score was worked out · GenAI Arena: An Open Evaluati… 38%, EvalAlign: Supervised Fine-Tu… 33%, ImagenHub: Standardizing the… 16% 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 |
|---|---|---|
 GenAI Arena: An Open Evaluation Platform for Generative Models (arXiv v3) | 1 | 38% |
| EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3) | 1 | 33% |
| ImagenHub: Standardizing the evaluation of conditional image generation models (arXiv v4) | 1 | 16% |
| HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1) | 1 | 11% |
 tgxs002/HPSv2 repository README, HPS v2 benchmark table | 1 | 0% |
| prior · pull toward the middle | 2% | |
| weighted average | = 27.6 |
$ 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