Superseded by Reve 2.1 a month after launch, so this page is mainly of historical interest; pricing came from a third party.
Kenning's take
What it does
Reve 2.0 is an image model that plans each picture as a layout of objects, text and regions, so users can move a subject, rewrite a sign or swap a background and the rest of the scene adjusts. It renders in native 4K, handles text and logos well and accepts more reference images than earlier versions. It replaced all earlier Reve models in the Reve app and was itself followed by Reve 2.1 a month later.
- Images built from editable layouts
- Native 4K output
- Clean text, signs and logos
- Multiple reference images in one composition
- Rebuilt editor with object-level controls
Who it suits. People making ads, designs and creative images who want to edit parts of a picture.
Key facts
- Category
- AI models
- Part of
- Reve
- Made by
- Reve AI, Inc
- Released
- 3 June 2026
- How to get it
- was the default model at reve.com from June 2026; replaced by Reve 2.1 on 9 July 2026
- Works on
- Web
- Free plan
- Free plan with daily energy refresh; free accounts are opted into model training (as reported by eesel.ai)
Pricing
| Plan | Price | Billed |
|---|---|---|
| Lite | $7.99 plus tax | Not stated |
| Pro | $19.99 plus tax | Not stated |
FAQ
When was Reve 2.0 released?
Reve launched Reve 2.0 on 3 June 2026.
What resolution does Reve 2.0 make?
It renders images in native 4K.
Is Reve 2.0 still the current model?
No. Reve released Reve 2.1 on 9 July 2026.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Reve 2.1
Reve's native-4K image model with element-level editing and better text in other scripts
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.
Amazon Nova 2
Amazon's second family of Nova AI models, covering reasoning, speech conversation and combined text-and-image generation.