wowsuch ai
Live

AuroraAI-ResearchModel

AuroraIMG-6M

AuroraIMG-6M is a 6.82-million-parameter text-to-image model that generates 64×64 RGB images from short English captions. Its weights are available under the Apache 2.0 license, and the model can run on a CPU.

What it does

Use it to generate small images from simple English prompts or to experiment with compact generative models.

Availability
Model weights available on Hugging Face
Pricing model
Not established
Deployment
Can run on CPU
Privacy
No extra safety filtering of data or outputs.
Licence
Apache 2.0
Capability
image generation
Modality
textimage
Access
open weightsSDK
Deployment
on-premises
Pricing
unknown
Target user
developerresearchercreator

Evidence

6 claims
  • Generates 64×64 RGB images from short English captions. [1]
    It generates 64×64 images from short English captions, and every part of it was trained from scratch on CC12M.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model has 6.82M parameters, including the text encoder, denoiser, and VAE. [1]
    AuroraIMG-6M is a text-to-image model that's just **6.82M parameters**, and that number includes everything: the text encoder, the denoiser and the VAE.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • Model weights are released under the Apache 2.0 license. [1]
    The model weights are released under the Apache 2.0 license.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model is small enough to run on CPU. [1]
    The model is small enough to run on CPU.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • Short, lowercase, caption-style prompts work best. [1]
    **Prompting tips.** It was trained on CC12M alt-text, so short, lowercase, caption-style prompts work best ("a dog running on green grass", "a snowy mountain with blue sky").
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
  • The model is English-only and supports up to 62 caption tokens. [1]
    AuroraIMG-6M is a text-to-image model that's just **6.82M parameters**, and that number includes everything: the text encoder, the denoiser and the VAE.
    Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.

Sources

1
1
Hugging FaceOwner-controlled
https://huggingface.co/AuroraAI-Research/AuroraIMG-6M Retrieved 2026-10-27 01:40 UTC
Verified

Versions

2
VersionEffectiveChangeChanged fieldsState
22026-10-13 03:12 UTCmaterial changeavailability, deploymentCurrent
12026-10-12 04:02 UTCpublicationNoneCurrent

In briefs

1

Open in the catalog

Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.