Image / video / 3D generation

Image editing (gpt-image-1 reference)

gpt-image-1 supports image-to-image — pass reference_image_b64 for style transfer / partial edits.

python

import base64
from nexevo_ai import Nexevo

with open("input.png", "rb") as f:
    ref_b64 = base64.b64encode(f.read()).decode()

client = Nexevo()
r = client.images.generate(
    model="gpt-image-1",  # 注:DALL-E 3 / FLUX 也支持,Imagen 仅部分版本
    prompt="add a watercolor painting style",
    reference_image_b64=ref_b64,
    size="1024x1024",
)
print(r["data"][0]["url"])

Get a free API key →Go to Playground and try it →