Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT parameters, it reaches state-of-the-art performance among open-weight text-to-image models.
| Date | Stars |
|---|---|
| 2026-07-31 | 494 |
| 2026-08-01 | 494 |
| 2026-08-06 | 494 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center"> <h1> ERNIE-Image </h1> </div> <p align="center"> <a href="https://huggingface.co/Baidu/ERNIE-Image">🤗 ERNIE-Image</a> | <a href="https://huggingface.co/Baidu/ERNIE-Image-Turbo">🤗 ERNIE-Image-Turbo</a> | <a href="https://huggingface.co/spaces/baidu/ERNIE-Image">🖥️ Huggingface Demo</a> | <a href="https://aistudio.baidu.com/application/detail/179775">🖥️ AI Studio Demo</a> | <a href="https://yiyan.baidu.com/blog/posts/ernie-image">📖 Blog</a> | <a href="https://ernieimageprompt.com/">🖼️ Art Gallery</a> <br/> <a href="https://github.com/baidu/ERNIE-Image/blob/main/assets/contacts/WeChat_small.jpg">💬 WeChat(微信)</a> | <a href="https://discord.gg/ByUTbjfG5k">🫨 Discord</a> | <a href="https://x.com/ErnieforDevs">🏷️ X</a> </p> ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT) and paired with a lightweight Prompt Enhancer that expands brief user inputs into richer structured descriptions. With only 8B DiT parameters, it reaches state-of-the-art performance among open-weight text-to-image models.  **Highlights:** - **Compact but strong**: Despite its compact 8B DiT scale, ERNIE-Image remains highly competitive with substantially larger open-weight models across a range of benchmarks. - **Text rendering**: Performs particularly well on dense, long-form, and layout-sensitive text, making it a strong choice for posters, infographics, UI-like images, and other text-heavy visual content. - **Instruction following**: Able to follow complex prompts involving multiple objects, detailed relationships, and knowledge-intensive descriptions with strong reliability. - **Structured generation**: Especially effective for structured visual tasks such as posters, comics, storyboards, and multi-panel compositions. - **Style coverage**: Supports realistic photography, design-oriented imagery, and distinctive stylized aesthetics. - **Practical deployment**: Can run on consumer GPUs with 24G VRAM. ## Released Versions | Model | Description | Inference Steps | CFG | |-------|-------------|-----------------|-------| | [ERNIE-Image](https://huggingface.co/baidu/ERNIE-Image) | SFT model with stronger general-purpose capability and instruction fidelity | 50 steps | 4.0 | | [ERNIE-Image-Turbo](https://huggingface.co/baidu/ERNIE-Image-Turbo) | Turbo model optimized by DMD and RL for faster speed and higher aesthetics | 8 steps | 1.0 | ## Benchmark ### GenEval | Model | Single Object | Two Object | Counting | Colors | Position | Attribute Binding | Overall | |---|---:|---:|---:|---:|---:|---:|---:| | ERNIE-Image (w/o PE) | **1.0000** | 0.9596 | 0.7781 | 0.9282 | 0.8550 | **0.7925** | **0.8856** | | ERNIE-Image (w/ PE) | 0.9906 | 0.9596 | 0.8187 | 0.8830 | **0.8625** | 0.7225 | 0.8728 | | Qwen-Image | 0.9900 | 0.9200 | **0.8900** | 0.8800 | 0.7600 | 0.7700 | 0.8683 | | ERNIE-Image-Turbo (w/o PE) | **1.0000** | **0.9621** | 0.7906 | 0.9202 | 0.7975 | 0.7300 | 0.8667 | | ERNIE-Image-Turbo (w/ PE) | 0.9938 | 0.9419 | 0.8375 | 0.8351 | 0.7950 | 0.7025 | 0.8510 | | FLUX.2-klein-9B | 0.9313 | 0.9571 | 0.8281 | 0.9149 | 0.7175 | 0.7400 | 0.8481 | | Z-Image | **1.0000** | 0.9400 | 0.7800 | **0.9300** | 0.6200 | 0.7700 | 0.8400 | | Z-Image-Turbo | **1.0000** | 0.9500 | 0.7700 | 0.8900 | 0.6500 | 0.6800 | 0.8233 | ### OneIG-EN | Model | Alignment | Text | Reasoning | Style | Diversity | Overall | |---|---:|---:|---:|---:|---:|---:| | Nano Banana 2.0 | 0.8880 | 0.9440 | 0.3340 | **0.4810** | **0.2450** | **0.5780** | | Seedream 4.5 | 0.8910 | **0.9980** | 0.3500 | 0.4340 | 0.2070 | 0.5760 | | ERNIE-Image (w/ PE) | 0.8678 | 0.9788 | **0.3566** | 0.4309 | 0.2411 | 0.5750 | | Seedream 4.0 | **0.8920** | 0.9830 | 0.3470 | 0.4530 | 0.191
Excerpt of 18,714 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:66589c15e40d8156, desc:text-to-image, desc:image generation