Image generation
Image generation · 73 endpoints
- black-forest-labs/flux-schnellGenerate up to four images quickly from a text prompt with the official FLUX Schnell model.
- Google: Gemini 3.1 Flash Image (Nano Banana 2)Generate or edit one image with Gemini 3.1 Flash Image at 512px, 1K, 2K or 4K on Google's own API, from a prompt and optional reference images; the image returns inline as base64.
- Google: Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)Generate or edit one 1K image with Gemini 3.1 Flash Lite Image on Google's own API, the cheapest Gemini image model; the image returns inline as base64.
Gemini 3 Pro image generation
- Google: Gemini 3 Pro Image (Nano Banana Pro)Generate or edit one image with Gemini 3 Pro Image at 1K, 2K or 4K on Google's own API, from a prompt and optional reference image URLs; the image returns inline as base64.
- Google: Gemini 3 Pro Image (Nano Banana Pro)Generate or edit an image with Gemini 3 Pro Image at 1K, 2K or 4K from a prompt and up to 14 reference images.
- Google: Gemini 3 Pro Image (Nano Banana Pro)Generate or edit one image with Gemini 3 Pro Image at 1K, 2K or 4K, from a prompt and up to 14 reference images.
- google/nano-banana-proGenerate or edit one image with Gemini 3 Pro Image (Nano Banana Pro) at 1K, 2K or 4K through Replicate's official model.
GPT Image 2.5 image generation
- OpenAI: GPT Image 2.5 (Flare / Sunburst)Generate images with GPT Image 2.5 through PiAPI's OpenAI-shaped async route, metered by quality and size.
- OpenAI: GPT Image 2.5 (Flare / Sunburst)Generate or edit images with GPT Image 2.5. Flare is the fast default; Sunburst is the precise editor. The -official models are OpenAI's own metered channel, priced by quality and size; the flat-rate channel had no upstream capacity when listed.
- openai/gpt-image-2.5-flareGenerate or edit images with GPT Image 2.5 Flare through Replicate's official model, priced per image by quality.
- openai/gpt-image-2.5-sunburstGenerate or edit images with GPT Image 2.5 Sunburst through Replicate's official model, priced per image by quality.
GPT Image 2 image generation
- OpenAI: GPT Image 2Generate images with GPT Image 2 (medium quality only) through PiAPI's OpenAI-shaped async route.
- OpenAI: GPT Image 2Generate or edit one image with GPT Image 2 at a flat per-resolution price.
- openai/gpt-image-2Generate or edit images with GPT Image 2 through Replicate's official model, priced per image by quality.
- MiniMax: image-01Generate one or more images synchronously from a text prompt.
Account and utility endpoints
- black-forest-labs/flux-1.1-pro-ultraFLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.
- black-forest-labs/flux-2-flexMax-quality image generation and editing with support for ten reference images
- black-forest-labs/flux-2-klein-4bVery fast image generation and editing model. 4 steps distilled, sub-second inference for production and near real-time applications.
- black-forest-labs/flux-2-maxThe highest fidelity image model from Black Forest Labs
- black-forest-labs/flux-2-proHigh-quality image generation and editing with support for eight reference images
- black-forest-labs/flux-devA 12 billion parameter rectified flow transformer capable of generating images from text descriptions
- black-forest-labs/flux-dev-loraA version of flux-dev, a text to image model, that supports fast fine-tuned lora inference
- black-forest-labs/flux-kontext-maxA premium text-based image editing model that delivers maximum performance and improved typography generation for transforming images through natural language prompts
- black-forest-labs/flux-kontext-proA state-of-the-art text-based image editing model that delivers high-quality outputs with excellent prompt following and consistent results for transforming images through natural language
- black-forest-labs/flux-proState-of-the-art image generation with top of the line prompt following, visual quality, image detail and output diversity.
- bria/fiboSOTA Open source model trained on licensed data, transforming intent into structured control for precise, high-quality AI image generation in enterprise and agentic workflows.
- bria/image-3.2Commercial-ready, trained entirely on licensed data, text-to-image model. With only 4B parameters provides exceptional aesthetics and text rendering. Evaluated to be on par to other leading models in the market
- bytedance/seedream-3A text-to-image model with support for native high-resolution (2K) image generation
- bytedance/seedream-4Unified text-to-image generation and precise single-sentence editing at up to 4K resolution
- bytedance/seedream-4.5Seedream 4.5: Upgraded Bytedance image model with stronger spatial understanding and world knowledge
- bytedance/seedream-5-liteSeedream 5.0 lite: image generation with built-in reasoning, example-based editing, and deep domain knowledge
- google/imagen-3Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty
- google/imagen-3-fastA faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality
- google/imagen-4Google's Imagen 4 flagship model
- google/imagen-4-fastUse this fast version of Imagen 4 when speed and cost are more important than quality
- google/imagen-4-ultraUse this ultra version of Imagen 4 when quality matters more than speed and cost
- google/nano-bananaGoogle's latest image editing model in Gemini 2.5
- google/nano-banana-2Google's fast image generation model with conversational editing, multi-image fusion, and character consistency
- ideogram-ai/ideogram-v2An excellent image model with state of the art inpainting, prompt comprehension and text rendering
- ideogram-ai/ideogram-v2-turboA fast image model with state of the art inpainting, prompt comprehension and text rendering.
- ideogram-ai/ideogram-v2aLike Ideogram v2, but faster and cheaper
- ideogram-ai/ideogram-v2a-turboLike Ideogram v2 turbo, but now faster and cheaper
- ideogram-ai/ideogram-v3-balancedBalance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles
- ideogram-ai/ideogram-v3-qualityThe highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles
- ideogram-ai/ideogram-v3-turboTurbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
- leonardoai/lucid-originArtistic and high-quality visuals with improved prompt adherence, diversity, and definition
- luma/photonHigh-quality image generation model optimized for creative professional workflows and ultra-high fidelity outputs
- luma/photon-flashAccelerated variant of Photon prioritizing speed while maintaining quality
- minimax/image-01Minimax's first image model, with character reference support
- openai/gpt-image-1.5OpenAI's latest image generation model with better instruction following and adherence to prompts
- prunaai/flux-fastThis is the fastest Flux endpoint in the world.
- prunaai/hidream-l1-fastThis is an optimised version of the hidream-l1 model using the pruna ai optimisation toolkit!
- prunaai/p-imageA sub 1 second text-to-image model built for production use cases.
- prunaai/p-image-loraUse trained LoRAs from the https://replicate.com/prunaai/p-image-trainer. Find or contribute LoRAs here https://huggingface.co/collections/PrunaAI/p-image-loras
- prunaai/wan-2.2-imageThis model generates beautiful cinematic 2 megapixel images in 3-4 seconds and is derived from the Wan 2.2 model through optimisation techniques from the pruna package
- prunaai/z-image-turboZ-Image Turbo is a super fast text-to-image model of 6B parameters developed by Tongyi-MAI.
- quiverai/arrow-1.1Generate editable SVG graphics from text prompts with Quiver's Arrow 1.1 model. Great for icons, logos, and illustrations.
- quiverai/arrow-1.1-maxGenerate high-fidelity SVG graphics from text prompts with Quiver's Arrow 1.1 Max model. Tuned for dense illustrations, detailed logos, and technical diagrams.
- qwen/qwen-imageAn image generation foundation model in the Qwen series that achieves significant advances in complex text rendering.
- recraft-ai/recraft-v3Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. As of today, it is SOTA in image generation, proven by the Text-to-Image Benchmark by Artificial Analysis
- recraft-ai/recraft-v3-svgRecraft V3 SVG (code-named red_panda) is a text-to-image model with the ability to generate high quality SVG images including logotypes, and icons. The model supports a wide list of styles.
- recraft-ai/recraft-v4-proRecraft's latest image generation model at ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-scale work.
- recraft-ai/recraft-v4-pro-svgGenerate detailed SVG vector graphics from text prompts. Recraft V4 Pro's design taste with more geometric detail and finer paths - clean layers, editable output, and scalable to any size.
- recraft-ai/recraft-v4-styles-pro-svgRecraft V4 Styles Pro SVG generates high-quality editable vector images that match a reusable style or attached reference images.
- recraft-ai/recraft-v4-svgGenerate production-ready SVG vector images from text prompts. Recraft V4's design taste applied to vector output - clean geometry, structured layers, and editable paths.
- sourceful/riverflow-2.0-proAgentic image model optimized for robust, high-precision generations supporting font control
- stability-ai/stable-diffusion-3.5-largeA text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, thanks to Query-Key Normalization.
- stability-ai/stable-diffusion-3.5-large-turboA text-to-image model that generates high-resolution images with fine details. It supports various artistic styles and produces diverse outputs from the same prompt, with a focus on fewer inference steps
- stability-ai/stable-diffusion-3.5-medium2.5 billion parameter image model with improved MMDiT-X architecture
- tencent/hunyuan-image-3A powerful native multimodal model for image generation (PrunaAI squeezed)
- wan-video/wan-2.7-imageGenerate and edit images with Alibaba's Wan 2.7
- wan-video/wan-2.7-image-proGenerate and edit high-quality images with Alibaba's Wan 2.7 Pro with 4K output, thinking mode, text-to-image, multi-image editing, and image set generation
- xai/grok-imagine-imageSOTA image model from xAI
These endpoints are callable but not part of the catalog's browse surface.