Image models
Image models
Every image model you can run in Nodaro, with what each one does and what it costs in credits.
Nodaro runs 54 image models. Each row below links to a page with the model's settings, credit prices and prompt tips.
Google
| Model | Maker | Modes | Credits | Details |
|---|
| Nano Banana 2 | Google | Text to image, Image to image | from 22 | Newer Nano Banana with native resolution control (1K/2K/4K) and Google Search context. |
| Nano Banana 2.1 | Google | Text to image, Image to image | from 11 | Google's high-efficiency image model for generation and editing — sharper quality, prompt adherence, character consistency and text rendering, up to 10 references and 4K output. |
| Nano Banana 2 Lite | Google | Text to image, Image to image | 11 | Lightweight Nano Banana 2 (Gemini 3.1 Flash-Lite) — fast, low-cost 1K generation and editing. |
| Nano Banana Pro | Google | Text to image, Image to image | from 50 | Top-tier Nano Banana — best for text rendering, diagrams, and complex compositions. |
| Nano Banana Edit | Google | Image editing | 11 | Image-to-image edits via Google's Nano Banana family. Good general-purpose editor. |
| Imagen 4 | Google | Text to image | 22 | Google's Imagen 4 — strong photographic quality and prompt fidelity. |
| Imagen 4 Fast | Google | Text to image | 11 | Cheaper / quicker Imagen 4 tier. |
| Imagen 4 Ultra | Google | Text to image | 33 | Premium Imagen 4 — highest fidelity, slower / more credits. |
Black Forest Labs
| Model | Maker | Modes | Credits | Details |
|---|
| Flux 2 Pro | Black Forest Labs | Text to image | from 15 | Flux 2 Pro text-to-image. Strong realism, fast. Resolution lever to 2K. |
| Flux 2 Pro (I2I) | Black Forest Labs | Image to image | from 15 | Image-to-image with Flux Pro. Cheaper than Flex variant, good general edits. |
| Flux Kontext Pro | Black Forest Labs | Text to image, Image editing | 15 | Context-aware editing and style transfer. Strong at preserving subject identity through edits. |
| Flux Kontext Max | Black Forest Labs | Text to image, Image editing | 28 | Premium Kontext — highest fidelity context-aware edits. |
| Flux 2 Klein (Open) | Black Forest Labs | Text to image | from 4 | Open Flux 2 9B from BFL — fast. |
| Kontext Multi (Open) | Black Forest Labs | Image to image, Image editing | 33 | Multi-image Flux Kontext Pro — up to 4 input images. |
| Flux 2 Pro (Safety Tolerance) | Black Forest Labs | Text to image, Image to image | from 14 | BFL Flux 2 Pro flagship. Accepts up to 4 reference images. |
| Flux 2 Max (Safety Tolerance) | Black Forest Labs | Text to image, Image to image | from 20 | BFL Flux 2 Max — even larger sibling of Pro, up to 8 reference images. Variable pricing by MP and ref count. |
| FLUX Fill Pro | Black Forest Labs | Image editing | 33 | Masked inpainting from BFL: repaints the mask's white area; the result keeps the image's size. |
OpenAI
| Model | Maker | Modes | Credits | Details |
|---|
| GPT Image 2 | OpenAI | Text to image | from 21 | Next-gen GPT Image — broader aspect ratios, resolution-based pricing (1K/2K/4K). |
| GPT Image 2 (I2I) | OpenAI | Image to image | from 21 | Image-to-image with GPT Image 2. |
| GPT Image 2.5 Flare | OpenAI | Text to image | from 17 | Fast everyday GPT Image 2.5 - higher quality than GPT Image 2 at about half the latency. The default of the pair: social and creator content, campaign variants, thumbnails, rapid iteration, high-volume work. |
| GPT Image 2.5 Flare (I2I) | OpenAI | Image to image | from 17 | Fast GPT Image 2.5 edits (up to 16 source images) - the default when you are iterating rather than finishing. |
| GPT Image 2.5 Sunburst | OpenAI | Text to image | from 17 | Precision GPT Image 2.5 - trades generation time for tighter control and detail fidelity. Pick it for brand-sensitive and production work: packaging, diagrams, ecommerce retouching, polished campaign creative. |
| GPT Image 2.5 Sunburst (I2I) | OpenAI | Image to image | from 17 | Precision GPT Image 2.5 edits (up to 16 source images) - the most controlled edit in the GPT family, at the cost of a longer run. |
| GPT Image 2.6 Flare | OpenAI | Text to image | from 9 | Fast GPT Image 2.6 - pick it for speed: posters, product shots and quick iteration, with stronger layouts. Up to 4K, quality from low to max or auto (priced up to the max), a transparent background at 1K. Writes PNG, JPEG, WebP, an animated GIF or an SVG. |
| GPT Image 2.6 Flare (I2I) | OpenAI | Image to image | from 19 | Fast GPT Image 2.6 edits - up to 16 input images, priced per image. Writes PNG, JPEG, WebP, an animated GIF or an SVG. Takes an inpainting mask (PNG, JPEG or WebP; the rest of the picture is kept as it was). Pick it while iterating. |
| GPT Image 2.6 Sunburst | OpenAI | Text to image | from 9 | Precision GPT Image 2.6 - pick it when every detail counts: the strongest consistency across edits and the finest detail. Up to 4K, quality from low to max or auto (priced up to the max), a transparent background at 1K. Writes PNG, JPEG, WebP, an animated GIF or an SVG. |
| GPT Image 2.6 Sunburst (I2I) | OpenAI | Image to image | from 19 | Precision GPT Image 2.6 edits - up to 16 input images, priced per image. Writes PNG, JPEG, WebP, an animated GIF or an SVG. Takes an inpainting mask (PNG, JPEG or WebP; the rest of the picture is kept as it was). Pick it for finished, detail-critical edits. |
Ideogram
| Model | Maker | Modes | Credits | Details |
|---|
| Ideogram V3 | Ideogram | Text to image | 20 | Strong typography and stylized illustration. Speed/quality tiered (TURBO/BALANCED/QUALITY). |
| Ideogram Edit | Ideogram | Image editing | from 33 | Inpainting / mask-based editing with Ideogram. Pair with a mask URL. |
Bytedance
| Model | Maker | Modes | Credits | Details |
|---|
| Seedream 5 Lite | Bytedance | Text to image | from 16 | Newer Seedream 5 Lite — instruction-based generation, visual reasoning. |
| Seedream 5 Lite (I2I) | Bytedance | Image to image | from 16 | Image-to-image with Seedream 5 Lite. |
| Seedream 5 Pro | Bytedance | Text to image | from 20 | Flagship Seedream 5 Pro — strongest instruction following and visual reasoning. Basic = 1K, high = 2K. |
| Seedream 5 Pro (I2I) | Bytedance | Image to image | from 21 | Image-to-image with Seedream 5 Pro — multi-reference instruction edits. Basic = 1K, high = 2K. |
| Seedream 5 Flash | Bytedance | Text to image | 11 | Fast, low-cost Seedream 5 — quick generations at 1K or 2K, same price at either size. |
| Seedream 5 Flash (I2I) | Bytedance | Image to image | 11 | Image-to-image with Seedream 5 Flash — fast edits from up to 10 input images at 1K or 2K, same price at either size. |
| Seedream 5.5 | Bytedance | Text to image | from 10 | Seedream 5.5 - more natural light, materials and skin, and dense small text that stays readable. A transparent background in one step, PNG or JPEG, at 1K, 1.5K or 2K (the default); 1K and 1.5K cost the same. |
| Seedream 5.5 (I2I) | Bytedance | Image to image | from 15 | Seedream 5.5 edits - change what you ask, round after round, and the rest of the picture stays as it was. Up to 10 input images, priced per image; a transparent background, PNG or JPEG, at 1K, 1.5K or 2K (the default). |
MiniMax
| Model | Maker | Modes | Credits | Details |
|---|
| MiniMax H3 Image | MiniMax | Text to image | from 6 | MiniMax H3 Image: detailed pictures up to about 16 MP at 4K, with readable text inside the picture. Ten shapes plus auto, the same price at 1K and 2K (2K by default), PNG or JPEG. |
| MiniMax H3 Image (I2I) | MiniMax | Image to image | from 7 | MiniMax H3 Image edits: change or combine up to 16 reference images in one edit, with readable text, up to about 16 MP at 4K. Priced by size and by reference image; auto keeps the first image's shape. |
Alibaba
| Model | Maker | Modes | Credits | Details |
|---|
| Qwen | Alibaba | Text to image | 11 | Cheap, fast, decent quality. Native negative-prompt support. |
| Qwen Edit | Alibaba | Image editing | 15 | Qwen image edit endpoint with native negative prompt. |
| Wan 2.7 | Alibaba | Text to image | from 22 | Wan 2.7 text-to-image — 1K/2K/4K, up to 9 optional style/character reference images. |
| Wan 2.7 Pro | Alibaba | Text to image | from 66 | Wan 2.7 Pro text-to-image — higher quality, 1K/2K/4K, no image input. |
Tongyi-MAI
| Model | Maker | Modes | Credits | Details |
|---|
| Z-Image | Tongyi-MAI | Text to image | 3 | Cheapest model in catalog. Fast, stylized output. Limited aspect ratios. |
xAI
| Model | Maker | Modes | Credits | Details |
|---|
| Grok Imagine | xAI | Text to image, Text to video | 11 | Expressive, high-contrast output. Supports both image and video. |
| Grok Imagine (I2I) | xAI | Image to image | 11 | Image-to-image with Grok. |
| Grok Imagine 2 | xAI | Text to image | 11 | Grok Imagine Image 2.0 — expressive, high-contrast t2i. Generations chain into grok-2-segment (free named region masks) and grok-2-edit (region-targeted edits). |
| Grok Imagine 2 Edit | xAI | Image editing | 11 | Prompt-edit a prior grok-2 generation by task id. Optional mask indexes (from grok-2-segment) restrict the edit to named regions. |
| Grok Imagine 2 (reference) | xAI | Image to image | 11 | grok-2 guided by ONE reference image — preserves the reference's composition while applying the prompt. |
| Grok Imagine 2 Segment Map | xAI | Image editing | 0 | FREE semantic segment map of a prior grok-2 generation — named region masks whose indexes feed grok-2-edit's region targeting. |
Recraft
| Model | Maker | Modes | Credits | Details |
|---|
| Recraft Remove BG | Recraft | Background removal | 4 | Remove image background. Cheap utility. |
| Recraft Crisp Upscale | Recraft | Image upscaling | 3 | Light-weight image upscale (Recraft Crisp). |
Topaz
| Model | Maker | Modes | Credits | Details |
|---|
| Topaz Image Upscale | Topaz | Image upscaling | from 28 | High-quality image upscale at 1x (enhance only), 2x or 4x. Best for production-ready output. |
Nodaro Upscale
| Model | Maker | Modes | Credits | Details |
|---|
| Nodaro Image Upscale | — | Image upscaling | from 5 | Image upscale at 1x (enhance only), 2x, 4x or 8x. Restores detail and keeps lettering exactly as written; the output is the input times the factor, nothing cropped. Priced by the output's size. |
Last updated on
Nodaro Docs