Generating an image from a prompt, editing an existing image and increasing its resolution call for different models. The catalog labels these tasks separately as images, image editing and upscaling. Choose the task first, then check the selected model’s controls in the workspace.
Image pricing can vary with resolution, quality, image count and other settings. A catalog rate and the charge for a particular request depend on its settings. Send your request to see the actual cost beside the result. Editing requires a source image, and supported formats and limits depend on the model.
Choose a model and send your request from the workspace. Its cost is calculated automatically and appears beside the result and in your history. Availability, capabilities and rates can change; check the selected model before sending a request.
82 models in this category · Updated:
wai-IllustriousAnime (WAI) is WAI-Illustrious, a community anime checkpoint built on Illustrious XL, for anime illustration, including uncensored adult content. It accepts prompts of up to 1,500 characters.
chromaChroma is an open-weight community text-to-image model based on FLUX.1 schnell, trained for uncensored, photorealistic generation. It accepts prompts of up to 7,500 characters.
firered-image-editFireRed is an instruction-following image editor that changes a source image from a natural-language request, with support for several reference images. It accepts prompts of up to 1,500 characters.
flux-2-maxFlux 2 Max is the top tier of Black Forest Labs' FLUX.2 image family, aimed at realism, precision and consistency. It pairs with Flux 2 Max Edit for editing with up to 6 input images.
flux-2-max-editFlux 2 Max Edit is the top FLUX.2 tier from Black Forest Labs for editing, built for realism, precision and consistency across up to 6 input images.
flux-2-proFlux 2 Pro is the Pro tier of Black Forest Labs' FLUX.2 image family, built for high-quality, prompt-faithful generation at speed. It handles detailed prompts of up to 3,000 characters.
flux-3-imageFlux 3 is Black Forest Labs' flagship image model, with native 2K and 4K output, precise layout control and strong text rendering. It accepts prompts of up to 32,000 characters and pairs with Flux 3 Edit for local edits and multi-reference composition.
flux-3-image-editFlux 3 Edit is Black Forest Labs' flagship image editor, made for precise local edits and multi-reference composition across up to 6 input images, with output up to 4K.
gpt-image-1-5GPT Image 1.5 is an earlier generation of OpenAI's GPT Image model, producing high-quality images in three aspect ratios. It pairs with GPT Image 1.5 Edit, which preserves composition, lighting and detail.
gpt-image-1-5-editGPT Image 1.5 Edit makes high-fidelity edits with OpenAI's GPT Image 1.5, preserving composition, lighting and detail. It takes up to 6 input images.
gpt-image-2GPT Image 2 is OpenAI's image generation model, known for fine typography and high detail. It renders at up to 4K, offers low, medium and high quality settings, and pairs with GPT Image 2 Edit for edits that preserve composition.
gpt-image-2-editGPT Image 2 Edit makes high-fidelity edits with OpenAI's GPT Image 2 that preserve the original composition. It takes up to 6 input images and renders at up to 4K.
gpt-image-2-5-flareGPT Image 2.5 Flare is the faster tier of OpenAI's GPT Image 2.5, built for quick, high-quality generation in creator and high-volume work. It renders at up to 4K and pairs with GPT Image 2.5 Flare Edit for scoped edits.
gpt-image-2-5-flare-editGPT Image 2.5 Flare Edit makes fast, scoped edits with OpenAI's GPT Image 2.5 while keeping the subject and composition intact. It takes up to 6 input images and renders at up to 4K.
gpt-image-2-5-sunburstGPT Image 2.5 Sunburst is the premium tier of OpenAI's GPT Image 2.5, built for precise, production-ready campaign and product imagery. It renders at up to 4K and pairs with GPT Image 2.5 Sunburst Edit for tightly controlled revisions.
gpt-image-2-5-sunburst-editGPT Image 2.5 Sunburst Edit gives tight control over edits with OpenAI's premium GPT Image 2.5 tier, holding the subject and composition steady across revisions. It takes up to 6 input images and renders at up to 4K.
gpt-image-2-6-flareGPT Image 2.6 Flare is the faster tier of OpenAI's GPT Image 2.6, giving high-fidelity results for campaign and product work at lower latency. It renders at up to 4K and pairs with GPT Image 2.6 Flare Edit.
gpt-image-2-6-flare-editGPT Image 2.6 Flare Edit makes fast, high-fidelity edits with OpenAI's GPT Image 2.6 Flare, keeping the subject and composition intact. It takes up to 6 input images and renders at up to 4K.
gpt-image-2-6-sunburstGPT Image 2.6 Sunburst is the high-fidelity tier of OpenAI's GPT Image 2.6, made for campaign and product work where detail matters. It renders at up to 4K and pairs with GPT Image 2.6 Sunburst Edit.
gpt-image-2-6-sunburst-editGPT Image 2.6 Sunburst Edit makes high-fidelity edits with OpenAI's GPT Image 2.6 Sunburst, keeping the subject and composition intact. It takes up to 6 input images and renders at up to 4K.
grok-imagine-imageGrok Imagine is xAI's image model, generating photorealistic images from text at 1K or 2K with reliable quality and low latency. It pairs with Grok Imagine Edit for changing elements and styles.
grok-imagine-editGrok Imagine Edit uses xAI's Grok Imagine to change an existing image from a text instruction: swap elements, restyle a scene or adjust details, at 1K or 2K.
grok-imagine-image-2-0Grok Imagine 2.0 is the second generation of xAI's Grok Imagine image model, generating images at 1K or 2K from text, with low and medium quality settings. It pairs with Grok Imagine 2.0 Edit for changing existing images.
grok-imagine-image-2-0-editGrok Imagine 2.0 Edit uses xAI's Grok Imagine 2.0 to change elements, styles and details of an existing image from a text instruction, at 1K or 2K with low and medium quality settings.
hunyuan-image-v3Hunyuan Image 3.0 is Tencent's open-weight text-to-image model, served here as the Instruct version, which reasons about a prompt before generating. It suits detailed, instruction-heavy prompts of up to 3,000 characters.
ideogram-v4Ideogram V4 is Ideogram's image model, known for legible, accurate text inside images. It suits posters, logos and marketing graphics.
ideogram-v4-5Ideogram V4.5 is Ideogram's typography-focused image model, rendering accurate text for posters, logos and designs at 1K or 2K. It offers low, medium and high quality settings and pairs with Ideogram V4.5 Edit.
ideogram-v4-5-editIdeogram V4.5 Edit is Ideogram's typography-aware image editor, changing images and the text within them. It takes up to 5 input images, the source plus up to 4 references, at 1K or 2K.
krea-2-turboKrea 2 Turbo is the speed-optimized, open-weight version of Krea's Krea 2 image model, generating high-fidelity images at 1K or 2K in seconds. It suits rapid ideation and iteration.
krea-3Krea 3 is the third generation of Krea's image model, rendering at up to 4K with built-in prompt expansion that fills in detail from short prompts. It offers medium and high quality settings and pairs with Krea 3 Edit for changing and combining images.
krea-3-editKrea 3 Edit changes an image from a text instruction and can combine up to 8 input images, rendering at up to 4K. It offers medium and high quality settings.
krea-v2-largeKrea v2 Large is Krea's high-fidelity text-to-image model, tuned for refined aesthetics and lifelike detail. It's the larger, higher-quality sibling of Krea v2 Medium.
krea-v2-mediumKrea v2 Medium is Krea's cost-effective text-to-image model, balancing speed and quality. It's the lighter sibling of Krea v2 Large.
luma-uni-1Luma Uni-1 is Luma AI's image model, which grounds prompts in web knowledge for faithful, high-fidelity results. It pairs with Luma Uni-1 Edit for text-guided edits that keep the source structure.
luma-uni-1-editLuma Uni-1 Edit makes text-guided edits with Luma AI's Uni-1 while preserving the structure of the source image.
luma-uni-1-maxLuma Uni-1 Max runs Luma AI's Uni-1 at maximum fidelity, for hero-quality stills with web-grounded prompt adherence. It pairs with Luma Uni-1 Max Edit.
luma-uni-1-max-editLuma Uni-1 Max Edit makes text-guided edits at maximum fidelity with Luma AI's Uni-1, preserving the structure of the source image.
lustify-sdxlLustify SDXL is a community fine-tune of Stable Diffusion XL, built for uncensored, adult-oriented photorealistic images. It accepts prompts of up to 1,500 characters.
lustify-v7Lustify v7 is version 7 of the Lustify community SDXL checkpoint, built for uncensored, adult-oriented photorealistic images. It accepts prompts of up to 1,500 characters.
lustify-v8Lustify v8 is version 8 of the Lustify community SDXL checkpoint, built for uncensored, adult-oriented photorealistic images. It accepts prompts of up to 1,500 characters.
minimax-h3-imageMiniMax H3 Image is MiniMax's image model for text-to-image generation, rendering at 1K, 2K and 4K in aspect ratios from 21:9 to 9:21. It pairs with MiniMax H3 Image Edit for changing and combining images.
minimax-h3-image-editMiniMax H3 Image Edit changes an image from a text instruction and can combine up to 16 input images, rendering at up to 4K.
muse-imageMuse Image is Meta's image model, known for faithful instruction following, accurate text and fine detail. It pairs with Muse Image Edit, which changes only what you ask and can compose from several reference images.
muse-image-editMuse Image Edit is Meta's Muse Image in editing mode. It changes only what you ask and can compose from up to 6 reference images.
nano-banana-2Nano Banana 2 is Google's Gemini-based image model, generating at up to 4K from prompts of up to 32,768 characters. It pairs with Nano Banana 2 Edit for fast, high-quality edits.
nano-banana-2-editNano Banana 2 Edit uses Google's Gemini-based Nano Banana 2 to edit images from a text instruction, combining up to 6 input images at up to 4K with fast turnaround.
nano-banana-2-liteNano Banana 2 Lite is the efficiency-focused tier of Google's Nano Banana 2 image models, built for fast, cost-effective generation. It pairs with Nano Banana 2 Lite Edit for quick multi-turn edits.
nano-banana-2-lite-editNano Banana 2 Lite Edit is Google's efficiency-focused image editor, built for fast multi-turn local edits with up to 6 input images.
nano-banana-2-1Nano Banana 2.1 is an update to Google's Gemini-based Nano Banana 2 image model, generating at up to 4K from prompts of up to 32,768 characters. It pairs with Nano Banana 2.1 Edit.
nano-banana-2-1-editNano Banana 2.1 Edit uses Google's Gemini-based Nano Banana 2.1 to edit images from a text instruction, combining up to 6 input images at up to 4K with fast turnaround.
nano-banana-proNano Banana Pro is the Pro tier of Google's Gemini-based Nano Banana image models, generating at up to 4K from prompts of up to 32,768 characters. It pairs with Nano Banana Pro Edit for high-quality edits.
nano-banana-pro-editNano Banana Pro Edit uses Google's Nano Banana Pro for high-quality edits from a text instruction, combining up to 6 input images at up to 4K.
qwen-edit-uncensoredQwen Edit Uncensored is an uncensored image editor based on Alibaba's Qwen image editing model, with improved quality and precision. It changes a source image from a natural-language instruction, without masks.
qwen-imageQwen Image is Alibaba's open-weight text-to-image model, known for close prompt adherence and accurate text rendering, including Chinese. It accepts prompts of up to 2,048 characters.
qwen-image-2Qwen Image 2 is Alibaba's Qwen Image 2.0 text-to-image model, with native 2K output and accurate typography. It pairs with Qwen Image 2 Edit for natural-language editing without masks.
qwen-image-2-editQwen Image 2 Edit is Alibaba's Qwen Image 2.0 in editing mode, changing an image from a natural-language instruction without masks.
qwen-image-2-proQwen Image 2 Pro is the highest-fidelity tier of Alibaba's Qwen Image 2.0, built for professional typography and detail. It pairs with Qwen Image 2 Pro Edit.
qwen-image-2-pro-editQwen Image 2 Pro Edit is the highest-fidelity tier of Alibaba's Qwen Image 2.0 for natural-language editing, built for precise, professional results.
qwen-image-2-1-proQwen Image 2.1 Pro is the full-capacity Qwen-Image 2.1 model from Alibaba, compact and efficient while generating at 1K or 2K. It pairs with Qwen Image 2.1 Pro Edit, which takes up to 10 reference images.
qwen-image-2-1-pro-editQwen Image 2.1 Pro Edit is the full-capacity Qwen-Image 2.1 editor, handling local edits and compositions of people and products from up to 10 reference images at 1K or 2K.
qwen-image-2-1-turboQwen Image 2.1 Turbo is the fast, cost-effective tier of Alibaba's open-weight Qwen-Image 2.1 series, balancing quality and speed at 1K or 2K. It pairs with Qwen Image 2.1 Turbo Edit.
qwen-image-2-1-turbo-editQwen Image 2.1 Turbo Edit is the fast tier of Alibaba's Qwen-Image 2.1 for editing: local edits, restyles and compositions from up to 6 input images at 1K or 2K.
qwen-image-3Qwen Image 3 is the standard tier of Alibaba's Qwen Image 3.0, offering cost-efficient text-to-image generation at 1K or 2K with strong text rendering. It pairs with Qwen Image 3 Edit.
qwen-image-3-editQwen Image 3 Edit is the standard tier of Alibaba's Qwen Image 3.0 for natural-language editing, cost-efficient and able to use multiple reference images at 1K or 2K.
qwen-image-3-proQwen Image 3 Pro is the Pro tier of Alibaba's Qwen Image 3.0, built for close prompt adherence and strong text rendering at 1K or 2K. It pairs with Qwen Image 3 Pro Edit.
qwen-image-3-pro-editQwen Image 3 Pro Edit is the Pro tier of Alibaba's Qwen Image 3.0 for natural-language editing with multiple reference images, at 1K or 2K.
recraft-v4Recraft V4 is Recraft's image model, known for high-quality output and precise text rendering. It suits design, branding and marketing work.
recraft-v4-proRecraft V4 Pro is the premium tier of Recraft V4, adding finer detail to its precise text rendering. It suits design, branding and product imagery where detail matters.
sd35SD35 is the provider’s deployment of Stable Diffusion 3.5 Large, Stability AI's open-weight text-to-image model. It favors artistic and painterly styles over strict photorealism and accepts prompts of up to 1,500 characters.
seedream-v4Seedream V4.5 is ByteDance Seed's image model, served uncensored, with strong composition and detail. It pairs with Seedream V4.5 Edit for natural-language editing.
seedream-v4-editSeedream V4.5 Edit is ByteDance Seed's Seedream 4.5 in editing mode, known for well-composed results from natural-language instructions, with up to 6 input images.
seedream-v5-liteSeedream V5 Lite is the fast tier of ByteDance Seed's Seedream 5.0 image models, giving high-quality images at lower latency. It pairs with Seedream V5 Lite Edit.
seedream-v5-lite-editSeedream V5 Lite Edit is the fast tier of ByteDance Seed's Seedream 5.0 for natural-language editing, with up to 6 input images.
seedream-v5-proSeedream V5 Pro is the flagship tier of ByteDance Seed's Seedream 5.0, generating high-quality images at 1K or 2K. It pairs with Seedream V5 Pro Edit.
seedream-v5-pro-editSeedream V5 Pro Edit is the flagship tier of ByteDance Seed's Seedream 5.0 for natural-language editing, at 1K or 2K with up to 6 input images.
seedream-v5-5Seedream V5.5 is ByteDance Seed's Seedream 5.5, generating high-quality images at 1K, 1.5K, or 2K with improved realism and text rendering. It pairs with Seedream V5.5 Edit.
seedream-v5-5-editSeedream V5.5 Edit is ByteDance Seed's Seedream 5.5 for natural-language editing, at 1K, 1.5K, or 2K with up to 10 input images.
upscalerUpscaler is the provider’s image upscaling model, enlarging an image 2x to 4x, up to 4096×4096 pixels. An optional creativity setting lets it add fine detail and texture as it scales.
wan-2-7-text-to-imageWan 2.7 is Alibaba's Wan 2.7 model in text-to-image mode, combining strong prompt understanding with high image quality. It handles prompts of up to 3,000 characters.
wan-2-7-pro-text-to-imageWan 2.7 Pro is the enhanced tier of Alibaba's Wan 2.7 for text-to-image generation, adding finer detail. It pairs with Wan 2.7 Pro Edit for editing with up to 6 input images.
wan-2-7-pro-editWan 2.7 Pro Edit is the premium tier of Alibaba's Wan 2.7 for natural-language image editing, combining up to 6 input images at 1K or 2K.
z-image-turboZ-Image Turbo is the distilled, fast version of Z-Image, an open-weight text-to-image model from Alibaba's Tongyi Lab. It produces high-quality images in a few steps, which makes it a good default for quick generation.
The UNCENSORED label comes from model specifications and identifies models designed for fewer refusals. It does not guarantee accuracy or an answer to every request. Max is a reasoning-effort setting on models that support it; each card lists the available modes. Rules and capabilities depend on the selected model.
OPEN THE INTERACTIVE CATALOG ↗