MIT HAN LabImage model
HART-0.7B-1024px
n/aUser voteshigher is better
n/aour own rating0 to 100
n/aper imagelower is better
0out of 100first value
Summary
HART-0.7B-1024px is an image model from MIT HAN Lab. HART is a hybrid autoregressive research model for direct text-to-image generation at 1,024 × 1,024 pixels.
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
The 100 most popular models of this category, 0 to 100, higher is more popular
20 of 100 models
Stability AI
CircleStone Labs and Comfy Org
Black Forest Labs
Krea.ai
OpenMOSS
OpenAI
Meituan
Microsoft
PixArt-Alpha
Tencent
DeepSeek
HiDream
Lodestones
inclusionAI
ByteDance Seed
Alpha-VLLM
VectorSpaceLab
Midjourney
Alibaba
StepFun
fal.ai
ByteDance
xAI
Krea
Show Lab, National University of Singapore
Meta
Kandinsky Lab
BAAI
Ideogram
NucleusAI
Reve
Luma Labs
Recraft
Adobe
Boogu Project
Bria
Zhipu AI
MIT HAN Lab
HUMAIN
AI Forever
Kuaishou
Leonardo AI
Luma AI
As of November 2026 · Source: gradually.ai popularity index
Over time
First value from November 2, 2026. The timeline appears from the second week.
Head-to-head comparisons
Show all comparisons (139)
All specifications
Architecture
Input and output
Licence and access
Further details
- Local inference
- Hybrid autoregressive research model for direct 1,024 × 1,024 text-to-image generation.
- Source: Local inference
- Additional runtime models
- The official example uses Qwen2-VL-1.5B as the text model; the Gradio demo can additionally use ShieldGemma-2B for safety filtering.
- Source: Additional runtime models
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | MIT HAN Lab (retrieved November 1, 2026) |
| Additional source | MIT HAN Lab (retrieved November 1, 2026) · MIT HAN Lab · Editorial description reviewed November 1, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |