Text to image and image editing routes, priced per image and callable with the same API key as everything else.
Z-Image Turbo is the distilled, speed-focused variant of Z-Image, a 6B-parameter open-weight image model from Alibaba's Tongyi-MAI team built on a single-stream diffusion transformer. It generates images from a text prompt in 8 sampling steps, with photorealistic output and English and Chinese text rendering.
Chroma1-HD is an 8.9B-parameter open-weight text-to-image model by lodestones (Lodestone Rock), derived from Black Forest Labs' FLUX.1 [schnell] and released under Apache 2.0. It is intended as a neutral base for fine-tuning and generates images from a text prompt, including adult content.
WAI-Illustrious-SDXL is a community anime checkpoint by the Civitai creator WAI0731, fine-tuned from OnomaAI's Illustrious XL, an SDXL-based model. It generates anime and illustration-style images from a text prompt, including adult content.
Lustify SDXL is a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt.
Lustify v7 (GGWP) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt.
Lustify v8 (APEX) is a release of Lustify, a community fine-tune of SDXL by the Civitai creator coyotte for photorealistic images, including adult content. It understands both natural-language prompts and Danbooru-style tags, and generates images from a text prompt.
Stable Diffusion 3.5 Large is Stability AI's 8B-parameter Multimodal Diffusion Transformer (MMDiT) text-to-image model, with improved image quality, typography and complex prompt understanding. It generates images from a text prompt.
HunyuanImage 3.0 is Tencent's open-weight native multimodal image model, unifying understanding and generation in one autoregressive framework. It uses a Mixture-of-Experts design with 80B total and 13B active parameters, generates images from a text prompt and can use reasoning to expand sparse prompts.
Wan 2.7 Pro is the high-fidelity tier of Wan 2.7, Alibaba's unified image generation and editing model family, with a focus on text rendering, brand colors and consistent multi-image output. This variant generates images from a text prompt at up to 4K resolution.
Wan 2.7 is Alibaba's unified image generation and editing model family. This standard tier has the same features as Wan 2.7 Pro, including text rendering and brand colors, with faster generation and a maximum resolution of 2048x2048. This variant generates images from a text prompt.
FLUX.2 [max] is the top tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one architecture. This variant generates images from a text prompt and can ground generation in real-time web context.
FLUX.2 [pro] is the production tier of Black Forest Labs' FLUX.2 image model family. FLUX.2 pairs a Mistral-3 vision-language model with a rectified flow transformer for generation and editing in one architecture. This variant generates images from a text prompt at up to 4 megapixels.
Seedream 4.5 is ByteDance Seed's image generation and editing model, scaled up from Seedream 4.0 with stronger typography, dense text rendering and closer preservation of reference details. This variant generates images from a text prompt.
Seedream 5.0 Lite is ByteDance Seed's unified multimodal image generation model with deep thinking and online search, which it uses to interpret the intent behind a prompt and depict current topics. This variant generates images from a text prompt.
Nano Banana 2 Lite (Gemini 3.1 Flash-Lite Image) is the speed- and cost-focused model in Google DeepMind's Nano Banana image family, built for high-volume generation and editing. This variant generates images from a text prompt.
Ideogram 4.0 is Ideogram's 9.3B-parameter open-weight text-to-image model, a single-stream diffusion transformer trained from scratch. It is built for in-image text and design layouts, with structured JSON prompts, bounding-box placement, hex color palettes and output up to 2K, including very wide aspect ratios.
Ideogram 4.5 is Ideogram's image generation and editing model, built for precise multi-turn edits that change part of an image while leaving the rest untouched. This variant generates images at native 2K from a text prompt, optionally guided by up to five reference images.
Krea 2 Large is the larger tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. It is more than twice the size of Krea 2 Medium with lighter post-training, giving rawer, more textured output suited to photorealism, and generates images from a text prompt with optional style references and moodboards.
Krea 2 Medium is the smaller, faster tier of Krea 2, Krea's foundation image model built from scratch for aesthetics and creative control over style. Its post-training keeps output stable across generations and suits illustration, anime and painting, and it generates images from a text prompt with optional style references and moodboards.
Uni-1 is Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant generates images from a text prompt, optionally guided by up to nine reference images.
Uni-1 Max is the higher-quality tier of Uni-1, Luma AI's unified understanding and generation model. It processes text and images in one interleaved sequence so that understanding of the prompt guides generation. This variant generates images from a text prompt, optionally guided by up to nine reference images.
Muse Image is Meta's image generation and editing model, the first from Meta Superintelligence Labs. It works with Meta's Muse Spark reasoning model to plan layouts, draw on web context and combine multiple references, and renders legible in-image text. This variant generates images from a text prompt.
GPT Image 1.5 is OpenAI's image generation model that takes text and image input, with improved instruction following and prompt adherence over earlier GPT Image models. This variant generates images from a text prompt.
Qwen-Image is a 20B-parameter open-weight MMDiT image foundation model from Alibaba's Qwen team, released under Apache 2.0. It generates images from a text prompt across many styles, with particular strength in rendering complex text, including Chinese.
Qwen-Image-2.0 is an image model from Alibaba's Qwen team that unifies generation and editing in one smaller, faster model, with instructions up to 1K tokens for infographics and native 2K resolution. This variant generates images from a text prompt.
Qwen-Image-2.0 Pro is the Pro tier of Qwen-Image-2.0, an image model from Alibaba's Qwen team that unifies generation and editing. It accepts instructions up to 1K tokens for infographics and has native 2K resolution. This variant generates images from a text prompt.
Qwen-Image-2.1 Pro is the Pro tier of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant generates images from a text prompt.
Qwen-Image-2.1 Turbo is an accelerated 8-step checkpoint of Qwen-Image-2.1, a 7B-parameter unified text-to-image and image editing model from Alibaba's Qwen team. It supports native transparent (RGBA) output, up to 10 reference images and 2K resolution. This variant generates images from a text prompt.
Qwen-Image-3.0 is the third-generation image model from Alibaba's Qwen team, built for dense layouts such as infographics, newspapers and storyboards. It accepts prompts up to 4.5k tokens and renders text as small as 10px, with native text in 12 languages. This standard tier is a faster version of Qwen-Image-3.0 Pro. This variant generates images from a text prompt.
Recraft V4 is Recraft's rebuilt image model focused on design taste, prompt accuracy and production-grade composition. This standard tier generates 1K images from a text prompt for everyday design work and fast iteration.
Recraft V4 Pro is the Pro tier of Recraft V4, Recraft's rebuilt image model focused on design taste and prompt accuracy. It generates 2K images from a text prompt with finer detail and better anatomy and realism in complex scenes, for high-detail, print-ready visuals.
