About Reve Models
Reve is a state-of-the-art text-to-image AI model known for its striking aesthetic quality, precise instruction following, and best-in-class typography rendering, consistently ranking among the top models on image generation leaderboards.
All Reve Models
Image Editing
reve/reve-remix
[Core Function] Reve Remix is Reve's multi-image composition model that blends 1 to 6 reference images guided by a text prompt. [Strengths] It excels at combining subjects, styles and elements from multiple references into one coherent image, and supports inline <img id></img> markers in the prompt to address specific input images by index. [Best For] Highly recommended for: merging subjects from different photos, transferring style from reference images, compositing a product into a new scene, and keeping a character consistent across references. [Limitations] Do NOT use this model for simple single-image edits; use Reve Edit for that. Do NOT use it for pure text-to-image generation; use Reve Create for that. It accepts between 1 and 6 reference images. [Routing] Choose this model when the user supplies multiple reference images to blend into a single result.
reve/reve-edit
[Core Function] Reve Edit is Reve's instruction-based single-image editing model. [Strengths] It excels at precise, localized edits that follow a natural-language instruction while preserving the untouched parts of the source image. [Best For] Highly recommended for: adding, removing or replacing objects, changing colors or attributes, adjusting style, and editing backgrounds on a single source image. [Limitations] Do NOT use this model to generate an image from scratch; use Reve Create for that. Do NOT use it to blend several images together; use Reve Remix for that. It requires exactly one reference image. [Routing] Choose this model when the user provides one image and wants targeted edits described in words.
