Craiyon
A rebranded AI model formerly known as DALL·E mini, Craiyon transforms text into images using advanced AI, while actively addressing biases from unfiltered internet data. Supported by Google TRC and spearheaded by Boris Dayma, it offers wide usage in creative image generation.
Features
- Text to Image Generation
- Ad-free
- Image to Image Generation
- Dark Mode
Craiyon News & Activities
Recent News
Recent activities
Danilo_Venom added Craiyon as alternative to Gemini Image
R_ex added Craiyon as alternative to Free Flash Image
duanhjlt added Craiyon as alternative to StringArtGenerator
POX added Craiyon as alternative to Qwen Image
Danilo_Venom added Craiyon as alternative to Imagine Draw AI
Featured in Lists
A list with 6 apps by Syrafire without a description.
What is Craiyon?
Craiyon, formerly DALL·E mini, is an AI model that can draw images from any text prompt!
Are you related to DALL·E mini?
Yes, Boris Dayma (who trained the current version of the AI model) and Pedro Cuenca (who worked on the backend) are both part of the craiyon team and still contribute to the dalle-mini repository!
Why did you change your name?
OpenAI asked us to change the name of our app which quickly became viral to avoid confusion with their model.
How does the AI model work?
The model used is called "DALL·E mini", specifically the larger version also known as "DALL·E mega" and is trained using Google TRC. You can find more details in the W&B Project Report.
What about limitations and biases?
While the capabilities of image generation models are impressive, they may also reinforce or exacerbate societal biases. Because the model was trained on unfiltered data from the Internet, it may generate images that contain harmful stereotypes. The extent and nature of the biases of the DALL·E mini model have yet to be fully documented. Work to analyze the nature and extent of these limitations is ongoing and being documented in more detail in the DALL·E mini model card.
Craiyon Videos
Craiyon information
Developed by
Boris Dayma Licensing
Open Source (Apache-2.0) and Freemium product.Pricing
Subscription ranging between $10 and $24 per month + free version with limited functionality.Written in
Alternatives
133 alternatives listedSupported Languages
- English
AlternativeTo Categories
AI Tools & Services, Photos & GraphicsGitHub repository
- 14,811 Stars
- 1,221 Forks
- 100 Open Issues
- Updated
Comments and Reviews
It's fast and fun! Unfortunately the new Craiyon webapp has a more limited license and seems to be closed source.
Reflecting on my recent experience, I can confidently say that the performance of the tool was a disaster. The results were subpar, failing to meet the standards set by similar platforms such as Mid journey or DALL·E. The user experience was severely compromised by the obnoxious amount of ads, making it almost unbearable to use.
On top of that, the platform's slow and cumbersome nature added to the frustration of the situation. It was poorly trained and unprepared for prime time, making it seem like a wasted opportunity. In the end, it was an exercise in frustration rather than productivity.
A good freebie for kids to play with, but it is by FAR no match to MS Copilot or Krita, as it had been suggested in a few places. It is good for what it is: a toy to play around like kids with crayons (as the title suggests). At one point it had somewhat better offers, but then something mysterious happened (perhaps bad competition bullying), and they were replaced with not-so-good presets. If you plan to draw-over and refine those sketches manually with a stylus, it might do the job for you. As for its "truly FREE" good alternative, try "Fusion Brain." If you want even better than them, try MS Copilot, whose free version is unbeatable, so far. There's only one drawback: it offers only 1:1 square pics good for post stamps and perhaps "fake" passport photos ;-)
It's better than Dall-E at least.
I was looking for an alternate to MidJourney, Craiyon has a long way to go, I can see that it will get there eventually, but images are unfortunately unusable at the moment
Not very good results at all as far as AI's go.
Not a good A.I drawer, faces are mess up and the images are to be used for personal reasons. You may also get errors a lot or wait in line a lot.
ai can't draw faces that well, it's not fb ai