whatmodel.sh / image / LLaDA-Image

LLaDA-Image

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

LLaDA-Image is an open-weights image model from Ant Group, released September 2026. Its published size is 6B parameters. Licence: apache-2.0.

Model information sources

Release date ↗ · Weights licence ↗ · Parameter count ↗

6B is stated for the family, covering both Base and Turbo; the card does not break down which components (e.g. VQ tokenizer/decoder) are inside the 6B.

55.1±2.6#65 of 144 image modelsfrom 6 benchmark results across 2 sources

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

$ how it compares

The image models ranked either side of LLaDA-Image, out of 197 with a score, then more from Ant Group.

#modelscorewhereRAMreleased
77Reve V1.1 Fast Reve56±4comparison only
78Z-Image-Turbo Alibaba (Tongyi-MAI)55±1api $0.0050/image +local~7.7GB2025-11
79LLaDA-Image Ant Group55±3local~22GB2026-09
80Qwen-Image-Edit Alibaba55±2api $0.030/image +local~27GB2025-08
81FLUX.2 [klein] Base 9B Black Forest Labs55±4comparison only2026-01
more from Ant Group
87LLaDA-Image-Turbo Ant Group54±3local~22GB2026-09

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

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #56 of 126 · 97% of its score · 6 tests

Beats HunyuanImage 2.1 here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
UltraText Bench (Composite, bilingual dense text rendering) lab43.9% ✎▁▂▂█▃▁▂▃·▁·▁ beats 10/22hard · avg 28%▇▇▇▇▇▇▇▇▇▇▇ 28%sharp · at its level · noisy
LongText-Bench (EN) lab92.3% ✎▃·····▅██▅▃▃ beats 5/12very easy · avg 88%▇▇▇▇▇▇▇▇ 19%small run
LongText-Bench (CN) lab91.3% ✎▃·······████ beats 4/12very easy · avg 89%▇▇▇▇▇▇ 15%maxed out · small run
GenEval lab85.0% ✎▇▃▅▇▁▄▅▃█▃▃▅ beats 33/39easy · avg 79%▇▇▇▇▇▇ 14%small run
CVTG-2K word accuracy lab87.5% ✎▄▄▄█▄▄·▄···▄ beats 6/8easy · avg 81%▇▇▇▇▇ 12%small run
DPG-Bench lab87.5% ✎▄·▂·▂▆█▄▃▄▂▂ beats 13/17very easy · avg 87%▇▇▇▇ 10%small run

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~21.6 GB · from github.com/leejet
    sd-cli --diffusion-model models/llada-image-q8_0.gguf --llm models/llada-image-text_encoder-q4_K.gguf --tokenizer models/tokenizer.json --vae models/llada_vae.safetensors --embeddings-connectors models/llada-image-connectors.safetensors --prompt "a lovely cat holding a sign says 'llada.cpp'" --width 1024 --height 1024 --steps 50 --cfg-scale 5.0 --seed 42 --output output.png

Weights and documentation: huggingface.co/inclusionAI ↗

$ how the score was worked out · LLaDA-Image: Building Strong… 70%, UltraText Bench: A Comprehens… 28%

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
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes · lab-reported5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 70%CC-BY-SA-4.0
UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation (arXiv:2610.09823v1) · lab-reported1▇▇▇▇▇▇▇▇ 28%CC-BY-4.0
prior · pull toward the middle▇ 3%
weighted average= 55.1

$ 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