Capability

    Image-to-image AI models

    18 Versely models list image-to-image among their capabilities — all of them image models, from 11 providers. What separates them is less what they do than what they need from you: 15 of them will not start without an image. The input table below is the part that actually decides which one you can use.

    18 models11 providers15 need a file to start16 reference images, max

    What you have to supply

    Capability tells you what a model produces. This tells you what it wants first, which is the part that decides whether you can use it today. 15 require a starting image and 12 accept reference images on top; anything not on that list runs from a text prompt alone.

    ModelYou must supplyIt will also take
    Flux 2 Klein 4B Base EditA starting imageUp to 4 reference images
    Pruna Image EditA starting imageUp to 5 reference images
    GPT Image 1 EditA starting imageUp to 6 reference images
    GPT Image 1.5A text prompt onlyUp to 16 reference images
    Qwen Image Edit 2511A starting imageUp to 6 reference images
    Seedream EditA starting imageUp to 10 reference images
    FireRed Image EditA starting imageUp to 3 reference images
    Kling Image O1A starting imageUp to 10 reference images
    Qwen Image 2 EditA starting imageUp to 3 reference images
    GPT Image 2.5 Flare EditA starting image—
    GPT Image 2.5 Sunburst EditA starting image—
    Mai Image 2.5 EditA starting image—
    Nano Banana 2A text prompt onlyUp to 14 reference images
    Runway Gen4 ImageA starting image—
    Seedream 4.5A text prompt onlyUp to 10 reference images
    Topaz Image ColorizationA starting image—
    Topaz Upscale ImageA starting image—
    HunyuanImage 3.0 Instruct EditA starting imageUp to 3 reference images

    Read straight off each model's own record — requires_image, requires_video_input, accepts_video_input, max_reference and the per-mode reference configuration. Nothing is inferred from a model's name or description.

    All 18 models

    Cheapest complete job first. Every row links to that model's spec page — tier and mode variants share a page with the model they are a variant of, so this is products rather than SKUs.

    ModelProviderCredits per jobCapabilities
    Flux 2 Klein 4B Base EditFlux1 creditalso edit image
    Pruna Image EditPrunaAI1 creditalso edit image
    GPT Image 1 EditOpenAI2 creditsalso edit image
    GPT Image 1.5OpenAI2 creditsalso text-to-image and edit image
    Qwen Image Edit 2511Qwen2 creditsalso edit image
    Seedream EditByteDance2 creditsalso edit image
    FireRed Image EditPrunaAI3 creditsalso edit image
    Kling Image O1Kling3 creditsalso edit image
    Qwen Image 2 EditQwen3 creditsalso edit image
    GPT Image 2.5 Flare EditOpenAI4-7 creditsalso edit image
    GPT Image 2.5 Sunburst EditOpenAI4-7 creditsalso edit image
    Mai Image 2.5 EditMicrosoft4 creditsalso edit image
    Nano Banana 2Google4 creditsalso text-to-image and edit image
    Runway Gen4 ImageRunway4-7 creditsthis only
    Seedream 4.5ByteDance4 creditsalso text-to-image and edit image
    Topaz Image ColorizationTopaz Labs7 creditsalso edit image
    Topaz Upscale ImageTopaz Labs7 creditsalso edit image
    HunyuanImage 3.0 Instruct EditHunyuan8 creditsalso edit image

    How these models are billed

    Five different billing shapes across the roster, which is why a straight comparison of headline figures between two of these models can mislead.

    • Charged a flat rate per generation8 models
    • Charged per megapixel of output5 models
    • Charged per image2 models
    • Charged quality resolution flat2 models
    • Charged a flat rate that changes with output resolution1 model

    All figures are Versely credits. A credit figure marked as a headline rate is not the cost of a complete job. Your plan's credit allowance is on the pricing page.

    More capability pages

    Every model on Versely · Model providers · Ranked buyer guides

    Frequently asked questions

    How many image-to-image models does Versely have?+

    18 with a spec page — all of them image models, from 11 providers. Tier and mode variants of the same model share a page with the model they are a variant of, so this is products rather than SKUs.

    What do image-to-image models need as input?+

    15 of the 18 require a starting image, 0 require a video file, 0 accept a video without requiring one and 12 take reference images (up to 16 on the most flexible). Anything not on that list runs from a text prompt alone, and every figure here is read off the model's own record rather than inferred from its name.

    What does an image-to-image job cost?+

    Complete jobs run 1 to 8 credits across the 18.

    Run every one of them on one subscription

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync — in your browser or on your phone.