Muse is a text-to-image model that also supports editing images through its generative transformer approach.
ERNIE
The ERNIE blog announces model releases and shares information about training and evaluation results.
About ERNIE
ERNIE is a Baidu AI model program. This page is its blog, which announces model releases and reports training and evaluation results. The posts cover ERNIE 5.0 and 5.1, ERNIE-Image, and PaddleOCR-VL-1.5. The blog reports leaderboard placements from LMArena and benchmark results for these models. The page does not describe how to access or use the models, and pricing is unknown.
Key features
- ERNIE-Image, a text-to-image model built on an 8B-parameter Diffusion Transformer
- ERNIE 5.0, a 2.4 trillion-parameter model that handles text, image, video, and audio
- ERNIE 5.1 release with reported Agent, reasoning, and creative capability upgrades
- PaddleOCR-VL-1.5, a document model reporting 94.5% accuracy on OmniDocBench v1.5
- Posts reporting LMArena leaderboard rankings for ERNIE models
Best for: Researchers and developers who want to follow ERNIE model releases and the reported training and evaluation results.
Good for
- Release posts give specific reported benchmark figures and leaderboard positions
- ERNIE-Image is described as achieving leading performance among open-weights models
- ERNIE 5.0 is described as integrating several media types in one autoregressive framework
Watch out for
- Performance figures are the blog's own reports of rankings and benchmarks, and the page does not describe the testing methods
- The page does not explain how to access or use the models
ERNIE at a glance
- Website
- ernie.baidu.com
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
ERNIE alternatives
Tools and sites you could use instead, ranked by how closely they match.
Google Research introduced Imagen as a text-to-image diffusion model in this research paper.
timm provides PyTorch image encoders and backbones along with training, evaluation, inference, and export scripts.
Open source
24 alternatives
TokenVerse presents research on personalizing image generation through multi-concept token modulation.
Image Arena ranks text-to-image generators and lets users compare sample outputs side by side.
Stable Diffusion v1.4 is a text-to-image model documented with its model card on Hugging Face.
Popular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aewTAObittensor.comAlpacacrfm.stanford.edu/2023/03/13/alpaca.htmlSmolVLAhuggingface.co/blog/smolvlaAI Indexhai.stanford.edu/ai-indexBloomhuggingface.co/docs/transformers/model_doc/bloom
ERNIE FAQ
What does the ERNIE blog cover?
It announces ERNIE model releases and shares information about training and evaluation results.
Is ERNIE-Image an open-weights model?
The blog describes ERNIE-Image as achieving leading performance among open-weights models. It does not state its license or where the weights are hosted.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.