whatmodel.sh / image / Dreamlike Photoreal 2.0

Dreamlike Photoreal 2.0

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Dreamlike Photoreal 2.0 is an open-weights image model from Dreamlike.art, released January 2023. Its published size is 0.86B parameters. Licence: dreamlike-modified-creativeml-openrail-m.

Catalogue identity notes

dreamlike-art/dreamlike-photoreal-2.0 (Stable Diffusion 1.5 fine-tune); 0.86B = UNet parameter count shown for the repository's safetensors on Hugging Face. Modified CreativeML OpenRAIL-M restricts hosting it as a service.

29.9±3.3#132 of 144 image modelsfrom 3 benchmark results across 3 sources

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of Dreamlike Photoreal 2.0, out of 197 with a score.

#modelscorewhereRAMreleased
176Janus-1.3B DeepSeek32±4local~5.5GB2024-10
177IF-M DeepFloyd31±3local~14GB2023-04
178Dreamlike Photoreal 2.0 Dreamlike.art30±3local~2.1GB2023-01
179AnyEdit (AnySD) Zhejiang University / NUS (AnyEdit)30±4comparison only2025-02
180Stable Diffusion v2.1 Stability AI29±2comparison only2022-12

see all image models · find the ones that fit your machine

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #110 of 126 * · 0.3% of its score · 1 test

Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ), VILA-U 7B (256px) here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
HPS v2 benchmark (4-style average)27.9% ✎▃··▃▅·▅·▅▅█▅ beats 14/14hard · avg 27%▇ 0.3%blunt · at its level
other tests2 not in a task · 95% of its score
testresultvs the others in its rundifficultycountswhy
EvalAlign human text-image alignment score4.5600 mean human alignment score ✎█▄▄·█·▄█▄▄·▄ beats 2/11avg 6.285 mean human alignment score▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 73%typical
HEIM text-image alignment (aspect win rate, v1.1.0)85.1% ✎▁····█▁·▃··▁ beats 8/9very easy · avg 92%▇▇▇▇▇▇▇▇▇ 22%sharp · at its level · noisy

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~2.6 GB, NVIDIA only · from huggingface.co/dreamlike-art (official)
    uv run --with diffusers --with transformers --with accelerate --with torch python -c "import torch; from diffusers import StableDiffusionPipeline; p=StableDiffusionPipeline.from_pretrained('dreamlike-art/dreamlike-photoreal-2.0', torch_dtype=torch.float16).to('cuda'); p('a cat holding a sign').images[0].save('out.png')"

Official weights and documentation: huggingface.co/dreamlike-art ↗

$ how the score was worked out · EvalAlign: Supervised Fine-Tu… 73%, HEIM: Holistic Evaluation of… 22%, tgxs002/HPSv2 repository READ… 0%

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

sourceresultsshare of the scorelicence
EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 73%CC-BY-4.0
HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1)1▇▇▇▇▇▇▇ 22%CC-BY-4.0
tgxs002/HPSv2 repository README, HPS v2 benchmark table1▇ 0%Apache-2.0
prior · pull toward the middle▇ 5%
weighted average= 29.9

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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