Reve 2.1 Edit applies precise natural-language changes to one reference image with native 4K output and accurate text rendering.
Added Jul 15, 2026
Approx. Price
$0.280 per image
Model Type
image-to-image
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
Up to 1
Reference/edit images accepted • Provider max 10 MB
Output Sizes
Aspect Ratio
Default
auto
Number of Images
Default
1
Output Format
Default
png
Options (3)
PNG, JPEG, WebP
Generated image format.
Resolution
Default
auto
Options (18)
auto (Automatic), 4:1 (4:1), 3:1 (3:1), 21:9 (21:9) +14 more
Benchmarks
Benchmarks
Human preference benchmarks sourced from LMArena.
Image Edit
#14 / 57
Arena Score
1374.2
Votes
20,823
Confidence Interval
1368.2 - 1380.2
Published 2026-09-30 · Matched as reve-2.1
LMArena DatasetExamples
Loading examples…
Related image models
Compare Reve 2.1 Edit with similar models from the same provider or model family.
Reve 2.1 Remix
reve/2.1/remixReve 2.1 Remix combines up to eight reference images into a controlled native-4K composition with strong spatial and text fidelity.
Reve 2.1 Create
reve/2.1/text-to-imageReve 2.1 plans complex scenes before rendering for precise composition, strong prompt adherence, fine text, and native 4K output.
ReVE Art
reve-text-to-imageReVE Art AI transforms natural language prompts into vivid, high-fidelity artwork. Supports multiple aspect ratios, stylistic flexibility, and seeded reproducibility.
Qwen Image 2.1 Edit
wavespeed-ai/qwen-image-2.1/editEdit from up to ten reference images with natural-language instructions, strong subject preservation, flexible framing, and native output up to 2K.
Qwen Image 2.1 Edit LoRA
wavespeed-ai/qwen-image-2.1/edit-loraEdit from up to ten references while applying up to three custom LoRAs for precise identity, product, or style control at up to 2K.
GPT Image 2.5 Flare Edit
openai/gpt-image-2.5/flare/editGPT Image 2.5 Flare edits images from natural-language instructions with up to 16 reference images. Supports quality levels from low to max and 1K, 2K, or 4K output. Pricing depends on quality, resolution, and reference image count.