Skip to content

Changelog

This document contains an history of all changes to the API.

  • 2024-Nov-29:

    • new endpoint for XL inpainting: /inpainting_sdxl
  • 2024-Nov-08:

    • add support for Flux loras produced by more training software (Xlabs, Kohya, TheLastBen)
  • 2024-Oct-23:

    • add support for Flux.1 D loras
  • 2024-Oct-21:

    • detect incompatible Flux Loras. Incompatible loras now produce a validation error instead of having no effect.
  • 2024-Oct-13:

    • supports lora parameters for a wider range of model architectures: Flux + SDXL + SDXL-Lightning
  • 2024-Sep-16:

    • bump max lora count to 4 and max lora size to 170 MB
  • 2024-Sep-13:

    • add steps parameter to /text2image_flux
  • 2024-Sep-07:

    • new endpoint to call the "Flux" model architecture: /text2image_flux
  • 2024-Jun-10:

    • new XL Lightning models: juggernautxl_10_hyper, ponyxl_6_turbo_dpo
    • new XL model: ponyxl_6
  • 2024-Apr-10:

    • new SD1 models: juggernaut_reborn, 0001softrealistic_v187, indigo_furry_mix_v120_hybrid, ghostmix_v2, dark_sushi_mix_v2_25d, arthemy_comics_gt_beta, art_universe_v8
  • 2024-Apr-04:

    • new endpoint to call models with "XL Lightning" architecture, offering faster & cheaper high-resolution generations: /text2image_sdxl_lightning
    • 3 new XL Lightning models:
      • juggernautxl_9_lightning_1024px: realistic
      • dreamshaperxl_lightning_1024px: general purpose
      • envy_starlight_xl_01_lightning_1024px: artistic
    • new sampler: dpm_single (DPM++ Single Step)
  • 2024-Jan-25:

    • WebP encoding support: you can now specify format=webp on all endpoints.
    • new SD1 models: analogmadness_7, realcartoon3d_13, realcartoonanime_10, realdream_12, yesmix_4
    • new SDXL model: juggernautxl_rundiffusion_8_1024px
    • updated SDXL model: BluePencilXL 0.8.0 -> 3.1.0 (same ID)
  • 2023-Dec-06:

    • new endpoint: /remove-background, given an image, automatically detect the main subject and replace the background with transparent pixels.
    • new parameter: transparent_background on the /text2image_sdxl function to automatically return transparent images (uses a pass of the same model as the function above with the same pricing)
    • new XL model: tshirtdesignredmond_1024px specifically tuned for the production of tshirt designs. Important: needs the trigger word TshirtDesignAF in your prompt!
  • 2023-Oct-24:

    • several backend optimizations
    • these optimizations enable us to offer a new revamped XL pricing (~50% price reduction with default settings)

    • XL model updates: JuggernautXL 1 -> 5, BluepencilXL 0.1.0 -> 0.8.0 (IDs unchanged)

    • XL new default value for steps (due to improved models): 30
    • XL new default value for model: juggernautxl_1024px (JuggernautXL 5)

    • new SD1 models: cyberrealistic_3_3, icbinp_seco, realistic_vision_5_1, rpg_5, toonify_2, dreamix_1, furrytoonmix

    • new inpainting models: cyberrealistic_3_3_inpaint, icbinp_seco_inpaint, realistic_vision_5_1_inpaint, anything_4_5_inpaint
  • 2023-Sep-05: new parameter format, allowing to control the output image encoding with either png or jpg

  • 2023-Aug-29:
    • new photorealistic XL model: juggernautxl_1024px
    • new general models: dreamshaper_8, absolute_reality_1_8_1, anylora, kidsmix
    • new inpainting models: dreamshaper_8_inpaint, absolute_reality_1_8_1_inpaint
  • 2023-Aug-21:
    • new endpoint /text2image_sdxl which supports Stable Diffusion XL inference.
    • 3 XL models: sdxl_1024px, dreamshaperxl_1024px, bluepencilxl_1024px
  • 2023-Jul-31:
    • added support for LoRA model inference on text2image, image2image & controlnet endpoints
    • /info: added new field family to distinguish the architecture family of a model.(ex: sd1, sd2, and future ones like sdxl)
  • 2023-Jul-13: added /controlnet endpoint
  • 2023-Jul-07: new models absolute_reality_1_6, dreamshaper_7 and nightmareshaper
  • 2023-Jul-05: added PayPal support to top-up your Dezgo balance
  • 2023-Jun-22: new sampler dpmpp_2m_karras (DPM++ 2M Karras), converges faster (less steps) and improves overall image quality
  • 2023-Jun-07: new models absolute_reality_1, cyberrealistic_3_1 and icbinp
  • 2023-May-24: new model dreamshaper_6
  • 2023-May-18: new models deliberate_2 and dreamshaper_5
  • 2023-Apr-27: new endpoint /edit-image providing access to the model Instruct-Pix2Pix, enabling general-purpose editing of images with text instructions
  • 2023-Apr-24: new prompt weighting syntax parser: adds support for the (word word:weight) syntax, and fixes bugs and slowdowns that would rarely occur in some edge cases
  • 2023-Apr-15: public release of the api.dezgo.com API, with documentation at dev.dezgo.com
  • 2023-Apr-04: added models Anything 5 and CyberRealistic 1.3
  • 2023-Apr-01: added /text-inpainting endpoint
  • 2023-Mar-20: several backend improvements to maximize infrastructure reliability
  • 2023-Mar-08: added prompt weighting
  • 2023-Mar-02: revamped the model list and associated documentation
  • 2023-Feb-26: the total number of supported diffusion models is now 57 + added a new "models" field in /info to be able to retrieve metadata about each model
  • 2023-Feb-10: support for request parameters serialized as JSON (in addition to FormData / Multipart)
  • 2023-Jan-07: added 7 new finetuned models:
    • synthwavepunk_v2
    • redshift_diffusion
    • analog_diffusion
    • disco_diffusion_style
    • iconsmi_appiconsmodelforsd
    • lowpoly_world
    • vintedois_diffusion_v0_1
  • 2022-Dec-21: added Real-ESRGAN upscaling, as a parameter on existing methods and as a new standalone /upscale method.
  • 2022-Dec-13:
    • multi-model selection for text2image/image2image (SD 1.4/1.5/SD 2.0 512px/SD 2.0 768px/SD 2.1 512px/SD 2.1 768px/WaifuDiffusion 1.3/Anything3.0/Trinart2.0)
    • specialized inpainting models (SD-inpaint-1/SD-inpaint-2)
    • negative_prompt
    • new samplers: DPM, Euler, Euler-Ancestral
    • default settings: DPM sampler with 30 steps
    • image resolutions can now be a multiple of 8px (instead of 64px previously)
  • 2022-Oct-22: upgrade the model to Stable Diffusion v1.5 + new finetuned autoencoder f8-ft-MSE. This provides incremental improvements to fine details like eyes, teeth, hands but also overall composition/proportions.
  • 2022-Oct-13: reduced minimum resolution to 320x320
  • 2022-Sep-18: added new methods: "image2image" and "inpainting"
  • 2022-Sep-17: added new "sampler" field with possible values: "k_lms", "ddim", "pndm"
  • 2022-Sep-17: bump the range of possible seed values to 4294967295 (unsigned 32-bit integer)
  • 2022-Sep-07: added response header x-input-seed, containing the seed used to generate the image (which can either be randomly generated by the API or chosen by the user)