whatmodel.sh / image / JanusFlow-1.3B

JanusFlow-1.3B

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

JanusFlow-1.3B is an open-weights image model from DeepSeek, released November 2024. Its published size is 1.3B parameters. Licence: deepseek.

Catalogue identity notes

DeepSeek JanusFlow-1.3B unified autoregressive + rectified-flow model (deepseek-ai/JanusFlow-1.3B, pinned ba75944; card: code under MIT, 'The use of JanusFlow models is subject to DeepSeek Model License'). MMMG Table 2 'JanusFlow-1.3B' (384 px). Comparison-only.

Model information sources

Release date ↗ · Weights licence ↗

1.3B as named by DeepSeek.

36.1±6.3comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

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

$ how it compares

The image models ranked either side of JanusFlow-1.3B, out of 197 with a score, then more from DeepSeek.

#modelscorewhereRAMreleased
160DALL·E 2 OpenAI36±3comparison only2022-04
161SSD-1B Segmind36±4local~3.3GB2023-10
162JanusFlow-1.3B DeepSeek36±6comparison only2024-11
163PixArt-α (PixArt-XL-2-1024-MS) PixArt (Huawei Noah's Ark Lab et al.)36±2local~14GB2023-11
164Emu3 BAAI36±2local~22GB2024-09
more from DeepSeek
153Janus-Pro-7B DeepSeek38±2api $0.0020/image +local~18GB2025-01
158Janus-Pro-1B DeepSeek36±4api $0.0005/image +local~5.5GB2025-01
176Janus-1.3B DeepSeek32±4local~5.5GB2024-10

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

$ what it's good at

text to image▁▂▇▇▆▅█▇▂▃▁▁ #125 of 157 * · 83% of its score · 1 test

Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ), Stable Diffusion XL 0.9 (base) here, though they rank higher overall. Trails PixArt-α (PixArt-XL-2-1024-MS) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
MMMG knowledge-image generation (MMMG-Score, average over education levels)9.8% ✎▃··▃·█▃▃▅··▃ beats 1/9hard · avg 24%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%typical

$ where to run it

No verified API or download recorded yet · add one

Weights and documentation: huggingface.co/deepseek-ai ↗

$ how the score was worked out · MMMG: A Massive, Multidiscipl… 83%

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
MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning (arXiv:2506.10963v2)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 83%CC-BY-SA-4.0
prior · pull toward the middle▇▇▇▇▇ 17%
weighted average= 36.1

$ 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