2025 releases · AI image

    Every AI image model released in 2025

    48 models from 19 providers, dated 1 March 2025 to 23 December 2025. They did not arrive evenly — they landed in 14 bursts, and this page is those bursts in order.

    The 2025 image timeline

    1–31 March 2025

    3 models · 3 providers

    HiggsField, Reve and Runway shipped 3 image models between 1 March 2025 and 31 March 2025. Of the 3, 1 has a spec page and 2 have no page of their own. Cheapest complete job in the window: 4 credits on Reve Text to Image. Highest output in it: 4K on Higgsfield.

    • New names on the roster: HiggsField, Reve, Runway.
    ModelBuilt byCredits per jobMax outputAspect ratios
    HiggsfieldAdvanced physics-inspired image generationHiggsField23 credits4K1:1, 16:9, 9:16, 2:3, 3:2
    Reve Text to ImageEfficient text-to-image generation with clarityReve4 credits4K16:9, 3:2, 4:3, 1:1, 3:4, 2:3
    Runway Gen4 ImageRunway Gen4 image generation model with high-quality creative outputs and style controlRunway5-8 credits1080p21:9, 16:9, 4:3, 1:1, 3:4, 9:16

    1–8 April 2025

    3 models · 3 providers

    Midjourney, PrunaAI and Runway shipped 3 image models between 1 April 2025 and 8 April 2025. Of the 3, 1 has a spec page, 1 is folded into a parent model's page as tier or mode variants and 1 has no page of its own. Cheapest complete job in the window: 1 credit on Pruna Text to Image. Highest output in it: 4K on Pruna Text to Image.

    • New name on the roster: PrunaAI.
    ModelBuilt byCredits per jobMax outputAspect ratios
    Pruna Text to ImageFast text-to-image generation with PrunaPrunaAI1 credit4K1:1, 16:9, 9:16, 4:3, 3:4, 3:2
    Midjourney V7Midjourney V7 text-to-image generation with photorealistic and artistic outputsMidjourney10 credits1:1, 16:9, 9:16, 4:3, 3:4, 2:3
    Runway Gen4 Image TurbovariantFast variant of Runway Gen4 image generation for rapid creative iteration with quality outputsRunway3 credits1080p16:9, 9:16, 4:3, 3:4, 1:1, 21:9

    23 April – 20 May 2025

    3 models · 2 providers

    Google and OpenAI shipped 3 image models between 23 April 2025 and 20 May 2025. Of the 3, 1 has a spec page, 1 is folded into a parent model's page as tier or mode variants and 1 has no page of its own. Cheapest complete job in the window: 2 credits on GPT Image 1 Edit. Highest output in it: 4K on GPT Image 1 Edit.

    • New names on the roster: OpenAI, Google.
    ModelBuilt byCredits per jobMax outputAspect ratios
    GPT Image 1 EditAI-powered image editing with GPT precisionOpenAI2 credits4K1:1, 2:3, 3:2, 16:9, 9:16
    Imagen 4Premium model for photorealistic results (text-only)Google4 credits4K16:9, 4:3, 1:1, 3:4, 9:16, auto
    Imagen 4 UltravariantUltra-high definition image generation from textGoogle6 credits4K1:1, 16:9, 9:16, 4:3, 3:4

    29 May – 1 June 2025

    3 models · 2 providers

    Flux and Topaz Labs shipped 3 image models between 29 May 2025 and 1 June 2025. Of the 3, 2 have a spec page and 1 is folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 2 credits on Flux Kontext. Highest output in it: 4K on Flux Kontext.

    ModelBuilt byCredits per jobMax outputAspect ratios
    Flux KontextContext-aware generation with coherent compositionsFlux2 credits4K1:1, 9:16, 16:9, 2:3, 3:2, 3:4
    Flux Kontext MaxvariantMaximum context-aware image generationFlux8 credits4K1:1, 16:9, 9:16, 4:3, 3:4, 3:2
    Topaz Image ColorizationAI-powered colorization of black-and-white images with natural, realistic color restorationTopaz Labs8 credits

    11 June – 28 July 2025

    3 models · 2 providers

    Grok and SeedVR shipped 3 image models between 11 June 2025 and 28 July 2025. Of the 3, 2 have a spec page and 1 has no page of its own. Cheapest complete job in the window: 1 credit on SeedVR Upscale. Highest output in it: 8K on SeedVR Upscale.

    • New names on the roster: SeedVR, Grok.
    ModelBuilt byCredits per jobMax outputAspect ratios
    SeedVR UpscaleVR-optimized image upscalingSeedVR1 credit8K1:1, 2:3, 3:2, 16:9, 9:16
    Grok Imagine ImageCreative image generation with Grok AIGrok2 credits4K20:9, 19.5:9, 2:1, 16:9, 3:2, 4:3
    Grok Imagine Image QualityxAI Grok Imagine Image (Quality tier) text-to-image. Quality-optimized generation up to 2K resolution with a wide range of aspect…Grok5 credits2K20:9, 19.5:9, 2:1, 16:9, 3:2, 4:3

    4–5 August 2025

    3 models · 2 providers

    Leonardo and Qwen shipped 3 image models between 4 August 2025 and 5 August 2025. Of the 3, 1 has a spec page, 1 is folded into a parent model's page as tier or mode variants and 1 has no page of its own. Cheapest complete job in the window: 1 credit on Qwen Image. Highest output in it: 4K on Qwen Image.

    • New names on the roster: Qwen, Leonardo.
    ModelBuilt byCredits per jobMax outputAspect ratios
    Qwen ImageHigh-quality realistic images with excellent detailQwen1 credit4K16:9, 3:2, 4:3, 1:1, 3:4, 2:3
    Qwen Image MaxvariantMaximum quality image generation with Qwen's most advanced visual AI modelQwen8 credits1:1, 16:9, 9:16, 4:3, 3:4
    Leonardo Lucid OriginLeonardo AI origin model with lucid generationLeonardo4 credits4K1:1, 16:9, 9:16, 3:2, 2:3, 4:5

    15–26 August 2025

    4 models · 2 providers

    Google and Qwen shipped 4 image models between 15 August 2025 and 26 August 2025. Of the 4, 1 has a spec page, 2 are folded into a parent model's page as tier or mode variants and 1 has no page of its own. Cheapest complete job in the window: 2 credits on Imagen 4 Fast. Highest output in it: 4K on Imagen 4 Fast.

    • Raised the reference-image ceiling to 14 — Nano Banana Edit.
    ModelBuilt byCredits per jobMax outputAspect ratios
    Imagen 4 FastvariantFast variant of Google Imagen 4 for quick generationGoogle2 credits4K1:1, 9:16, 16:9, 3:4, 4:3
    Qwen Image EditImage editing with Qwen AIQwen2 credits4K
    Nano BananaFast and efficient image generation with vibrant colorsGoogle4 credits4K1:1, 9:16, 16:9, 3:4, 4:3, 3:2
    Nano Banana EditvariantImage editing capabilities with NANO Banana modelGoogle2 credits4K21:9, 16:9, 3:2, 4:3, 5:4, 1:1

    9 September 2025

    4 models · 1 provider

    ByteDance shipped 4 image models on 9 September 2025. Of the 4, 1 has a spec page, 1 is folded into a parent model's page as tier or mode variants and 2 have no page of their own. Cheapest complete job in the window: 2 credits on Seedream 4.0. Highest output in it: 4K on ByteDance Seedream 4.

    • New name on the roster: ByteDance.
    ModelBuilt byCredits per jobMax outputAspect ratios
    ByteDance Seedream 4ByteDance advanced image generation with creative outputByteDance3 credits4K1:1, 4:3, 3:4, 16:9, 9:16, 3:2
    Seedream 4.0ByteDance Seedream 4.0 text-to-image. High-resolution generation (up to 4K) with multi-image output and built-in prompt…ByteDance2 credits4K21:9, 16:9, 3:2, 4:3, 1:1, 3:4
    Seedream 4.0 EditvariantImage editing with Seedream 4.5ByteDance2 credits4K21:9, 16:9, 3:2, 4:3, 1:1, 3:4
    Seedream EditAdvanced image editing with SeedreamByteDance2 credits4K1:1, 2:3, 3:2, 16:9, 9:16

    22–24 September 2025

    3 models · 2 providers

    Qwen and Wan shipped 3 image models between 22 September 2025 and 24 September 2025. Of the 3, 1 is folded into a parent model's page as tier or mode variants and 2 have no page of their own. Cheapest complete job in the window: 3 credits on Qwen Image Edit 2509. Highest output in it: 4K on Wan 2.5 Image to Image.

    • New name on the roster: Wan.
    ModelBuilt byCredits per jobMax outputAspect ratios
    Qwen Image Edit 2509variantQwen Image Edit 2509 is an image editing model from Alibaba that enables precise modifications to existing images based on…Qwen3 credits1:1, 16:9, 9:16, 4:3, 3:4
    Wan 2.5 Image to ImageImage-to-image transformation with WAN 2.5Wan5 credits4K16:9, 4:3, 1:1, 3:4, 9:16
    Wan Preview 2.5 Text to ImageText-to-image generation with WAN 2.5Wan5 credits4K1:1, 4:3, 3:4, 16:9, 9:16

    1–20 November 2025

    3 models · 2 providers

    Google and Imagine shipped 3 image models between 1 November 2025 and 20 November 2025. Of the 3, 2 are folded into a parent model's page as tier or mode variants and 1 has no page of its own. Cheapest complete job in the window: 4 credits on ImagineArt 1.5. Highest output in it: 4K on ImagineArt 1.5.

    • New name on the roster: Imagine.
    ModelBuilt byCredits per jobMax outputAspect ratios
    ImagineArt 1.5Emotional and artistic image generationImagine4 credits4K3:1, 16:9, 3:2, 4:3, 1:1, 3:4
    Nano Banana ProvariantProfessional image generation with Nano Banana ProGoogle15-30 credits4K1:1, 2:3, 3:2, 4:3, 3:4, 16:9
    Nano Banana Pro EditvariantProfessional image editing with Nano Banana ProGoogle8-15 credits4K21:9, 16:9, 3:2, 4:3, 5:4, 1:1

    25 November 2025

    3 models · 1 provider

    Flux shipped 3 image models on 25 November 2025. Of the 3, 1 has a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 3 credits on Flux 2 Pro.

    ModelBuilt byCredits per jobMax outputAspect ratios
    Flux 2 FlexFlexible image generation and editing model from the Flux 2 family with versatile creative controlsFlux5 credits16:9, 9:16, 1:1, 4:3, 3:4
    Flux 2 ProvariantProfessional-grade image generation with the Flux 2 Pro model for high-quality detailed outputsFlux3 credits16:9, 9:16, 1:1, 4:3, 3:4
    Flux 2 Pro EditvariantFlux 2 Pro is an advanced image editing model that allows users to modify and enhance images based on specific instructions. It…Flux3 credits16:9, 4:3, 1:1, 3:4, 9:16, auto

    27 November – 1 December 2025

    3 models · 3 providers

    Kling, Qwen and Z-Image shipped 3 image models between 27 November 2025 and 1 December 2025. Of the 3, 2 have a spec page and 1 has no page of its own. Cheapest complete job in the window: 1 credit on Z Image Turbo. Highest output in it: 4K on Z Image Turbo.

    • New names on the roster: Z-Image, Kling.
    ModelBuilt byCredits per jobMax outputAspect ratios
    Qwen Z ImageAdvanced image generation model with enhanced creative capabilitiesQwen2 credits21:9, 16:9, 3:2, 4:3, 1:1, 3:4
    Z Image TurboHigh-speed image generation with Z-ImageZ-Image1 credit4K1:1, 16:9, 9:16, 4:3, 3:4
    Kling Image O1Kling Image O1 is an advanced image generation model by Kuaishou that produces high-quality, detailed images from text prompts.…Kling3 credits2K21:9, 16:9, 3:2, 4:3, 1:1, 3:4

    4 December 2025

    3 models · 1 provider

    ByteDance shipped 3 image models on 4 December 2025. Of the 3, 3 have no page of their own. Cheapest complete job in the window: 4 credits on Seedream 4.5. Highest output in it: 4K on Seedream 4.5.

    ModelBuilt byCredits per jobMax outputAspect ratios
    Seedream 4.5Advanced image generation with Seedream 4.5ByteDance4 credits4K1:1, 2:3, 3:2, 4:3, 3:4, 16:9
    Seedream 4.5 EditImage editing with Seedream 4.5ByteDance4 credits4K1:1, 2:3, 3:2, 4:3, 3:4, 16:9
    Seedream 4.5 Text to ImageText-to-image generation with Seedream 4.5ByteDance4 credits4K1:1, 4:3, 3:4, 16:9, 9:16

    5–23 December 2025

    7 models · 5 providers

    Flux, Meituan and OpenAI and 2 other providers shipped 7 image models between 5 December 2025 and 23 December 2025. Of the 7, 4 have a spec page, 2 are folded into a parent model's page as tier or mode variants and 1 has no page of its own. Cheapest complete job in the window: 2 credits on GPT Image 1.5. Highest output in it: 4K on GPT Image 1.5.

    • Raised the reference-image ceiling to 16 — GPT Image 1.5.
    • New name on the roster: Meituan.
    ModelBuilt byCredits per jobMax outputAspect ratios
    LongCat EditLongcat Edit is an image editing model that supports long-context image understanding and precise editing based on detailed…Meituan15 credits
    Flux 2 MaxMaximum quality image generation with the Flux 2 Max model for ultra-detailed photorealistic outputsFlux7 credits16:9, 9:16, 1:1, 4:3, 3:4
    Flux 2 Max EditvariantMaximum quality image generation with the Flux 2 Max model for ultra-detailed photorealistic outputsFlux7 credits16:9, 4:3, 1:1, 3:4, 9:16, auto
    GPT Image 1.5GPT-powered image generation version 1.5OpenAI2 credits4K1:1, 2:3, 3:2
    Wan 2.6 ImagevariantImage-to-image transformation with WAN V2.6Wan3 credits4K16:9, 4:3, 1:1, 3:4, 9:16
    Wan 2.6 Text to ImageText-to-image generation with WAN V2.6Wan2 credits4K1:1, 4:3, 3:2
    Qwen Image Edit 2511Qwen Image Edit 2511 is an image editing model from Alibaba that enables precise modifications to existing images based on…Qwen2 credits1:1, 5:4, 4:5, 5:6, 3:2

    When 2025 was busy

    9 of the twelve months carried a image release; the busiest window was 5–23 December 2025, with 7.

    March 2025
    3
    April 2025
    4
    May 2025
    4
    June 2025
    2
    July 2025
    2
    August 2025
    7
    September 2025
    7
    November 2025
    8
    December 2025
    11

    Who shipped image in 2025

    ByteDance (7), Flux (7) and Google (7) led on volume. SKUs, not quality — four tiers of one model count four times.

    ProviderModelsSpec pagesFirstLatest
    ByteDance719 September 20254 December 2025
    Flux7329 May 202516 December 2025
    Google7220 May 202520 November 2025
    Qwen634 August 202523 December 2025
    Wan4124 September 202516 December 2025
    Grok2128 July 202528 July 2025
    OpenAI2023 April 202516 December 2025
    Runway2131 March 20258 April 2025
    HiggsField101 March 20251 March 2025
    Imagine101 November 20251 November 2025
    Kling111 December 20251 December 2025
    Leonardo105 August 20255 August 2025
    Meituan115 December 20255 December 2025
    Midjourney113 April 20253 April 2025
    PrunaAI101 April 20251 April 2025
    Reve1025 March 202525 March 2025
    SeedVR1111 June 202511 June 2025
    Topaz Labs111 June 20251 June 2025
    Z-Image1027 November 202527 November 2025

    What 2025 moved

    Firsts, measured against every image model released before them. “New name on the roster” is the provider label in the catalog, not the company — one lab can hold several labels.

    Dates are each model’s released_at value, walked in order and grouped until a window held 3 or more. Credits are what one complete generation costs per the model’s own price matrix; where it states none, the headline rate is shown and the model sits out the cheapest-in-window line.

    Other release years

    Frequently asked questions

    How many AI image models were released in 2025?+

    Versely's catalog carries 48 image models with a 2025 release date, from 19 providers, arriving in 14 launch windows between 1 March 2025 and 23 December 2025.

    What was the biggest AI image launch of 2025?+

    5–23 December 2025, with 7 image models from Flux, Meituan, OpenAI, Qwen and Wan. Of the 7, 4 have a spec page, 2 are folded into a parent model's page as tier or mode variants and 1 has no page of its own. Cheapest complete job in the window: 2 credits on GPT Image 1.5. Highest output in it: 4K on GPT Image 1.5.

    Which company released the most AI image models in 2025?+

    ByteDance, with 7 of the 48 image models dated 2025 — first on 9 September 2025, most recently on 4 December 2025. Flux shipped 7, Google shipped 7, Qwen shipped 6.

    What changed in AI image generation in 2025?+

    Measured against everything the catalog carried before it: New names on the roster: HiggsField, Reve, Runway; New name on the roster: PrunaAI; New names on the roster: OpenAI, Google.

    Run any 2025 image model in Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.