Image generation
Text-to-image: the models ranked by blind human-preference arenas, the apps that host them, node-based workflow platforms, and local apps that run open models on your GPU.
Models are ranked by Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1), then LMArena Text-to-Image Arena for models without a result on the first. Tools inherit the tier of the best model they offer. How we rank.
- Best overallSGPT Image 2.51,220 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1)
- Best valueAMuse ImageTier A for $0.01/image
- Best free startSChatGPTFree tier · from $20/mo · via GPT Image 2.5
- Best local (≤24 GB GPU)CFLUX.2 [dev]~24 GB VRAM · 1,000 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1)
- Tier: how close to the best result on the task's main public benchmark
- Outlined: a tool inherits the tier of the best model it offers
- No public result yet
- Cloud · Local: runs on your own hardware
Models
The engines themselves. Use them through an API or inside the apps on the right.
Apps
Ready-made apps with a UI: sign in or install, then start.
Workflow platforms
Node and canvas tools that chain several models into one pipeline.
Runtimes & APIs
Run open models on your own machine, or reach models and services through an API.
Quality vs. price
Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) score against API price (USD per image, log scale). Up and to the left is better; the line joins the models that nothing else beats on both.
- Closed models
- Open-weights models
- Best-value frontier
Show as table
| Model | Weights | Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Price | Frontier |
|---|---|---|---|---|
| GPT Image 2.5 | Closed | 1,220 | $0.21/image | Yes |
| Nano Banana 2.1 | Closed | 1,174 | $0.03/image | Yes |
| Grok Imagine Image 2.0 | Closed | 1,167 | $0.04/image | |
| MAI-Image-2.6 | Closed | 1,166 | $0.04/image | |
| Muse Image | Closed | 1,127 | $0.01/image | Yes |
| MAI-Image-2.6-Flash | Closed | 1,119 | $0.02/image | |
| FLUX 3 Image | Closed | 1,116 | $0.05/image | |
| Nano Banana Pro (Gemini 3 Pro Image) | Closed | 1,115 | $0.13/image | |
| Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) | Closed | 1,106 | $0.03/image | |
| Seedream 5.0 Pro | Closed | 1,100 | $0.09/image | |
| Qwen-Image-3.0-Pro | Closed | 1,094 | $0.04/image | |
| Krea 2 | Closed | 1,034 | $0.03/image | |
| Ideogram 4.0 | Open | 1,026 | $0.06/image | |
| Recraft V4.1 | Closed | 1,025 | $0.04/image | |
| Uni-1.1 | Closed | 1,022 | $0.04/image | |
| Ideogram 4.5 | Closed | 1,016 | $0.1/image | |
| Seedream 5.0 Lite | Closed | 1,016 | $0.04/image | |
| FLUX.2 [dev] | Open | 1,000 | $0.01/image | |
| Ming-Image-0.1-Design | Open | 999 | $0.03/image | |
| P-Image-Ideogram | Closed | 995 | $0.01/image | |
| Cosmos3-Super-Text2Image | Open | 992 | $0.04/image | |
| HunyuanImage 3.0 | Open | 989 | $0.03/image | |
| Wan 2.7 Image | Closed | 985 | $0.03/image | |
| HiDream-O1-Image | Open | 974 | $0.04/image | |
| Z-Image Turbo | Open | 934 | $0.0050/image | Yes |
| Kling IMAGE 3.0 Omni | Closed | 918 | $0.03/image | |
| ERNIE-Image-Turbo | Open | 914 | $0.01/image | |
| GLM-Image | Open | 888 | $0.05/image | |
| LongCat-Image | Open | 858 | $0.13/image |
Quality vs. setup
The same tools as the map, placed by how good the results can be (up) and how much setup they take (right). Top-left is the easiest way to top quality; further right buys control, privacy or price at the cost of setup. Models are left out: you reach them through these tools.
- Cloud
- Local: runs on your hardware
- Hollow: tier inherited from the best model the tool offers
Not placed (no public result yet): SD.Next, Draw Things, Microsoft Copilot, Midjourney, NovelAI, PixAI, Pixlr, Vidu, Wan
Everything, in order
| Tier | Name | Approach | Runs | Rated by | Price | Skill |
|---|---|---|---|---|---|---|
| S | OpenAI | Models | Cloud | 1,220 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.21/image | — |
| S | OpenAI | Apps | Cloud | via GPT Image 2.5 | Free tier · $20/mo | beginner |
| S | Comfy Org | Workflow platforms | Cloud | via GPT Image 2.5 | Free tier · $20/mo | advanced |
| S | ByteDance (CapCut) | Apps | Cloud | via GPT Image 2.5 | Free tier | beginner |
| S | fal | Runtimes & APIs | Cloud | via GPT Image 2.5 | — | intermediate |
| S | Fuser | Workflow platforms | Cloud | via GPT Image 2.5 | — | intermediate |
| S | getimg.ai | Apps | Cloud | via GPT Image 2.5 | $15/mo | beginner |
| S | Glif | Apps | Cloud | via GPT Image 2.5 | Free tier | beginner |
| S | Higgsfield AI | Apps | Cloud | via GPT Image 2.5 | — | beginner |
| S | ImagineArt | Apps | Cloud | via GPT Image 2.5 | $5/mo | beginner |
| S | Kittl | Apps | Cloud | via GPT Image 2.5 | Free tier | beginner |
| S | Krea | Apps + Workflow platforms | Cloud | via GPT Image 2.5 | Free tier · $5.25/mo | beginner |
| S | Leonardo.Ai (Canva) | Apps | Cloud | via GPT Image 2.5 | Free tier · $12/mo | beginner |
| S | Lovart | Apps | Cloud | via GPT Image 2.5 | Free tier | beginner |
| S | Mage | Apps | Cloud | via GPT Image 2.5 | Free tier · $10/mo | beginner |
| S | NightCafe Studio | Apps | Cloud | via GPT Image 2.5 | Free tier | beginner |
| S | OpenArt | Apps | Cloud | via GPT Image 2.5 | Free tier · $14/mo | beginner |
| S | Playground | Apps | Cloud | via GPT Image 2.5 | $15/mo | beginner |
| S | Replicate | Runtimes & APIs | Cloud | via GPT Image 2.5 | — | intermediate |
| S | Scenario | Apps + Workflow platforms | Cloud | via GPT Image 2.5 | Free tier · $15/mo | intermediate |
| S | SeaArt | Apps | Cloud | via GPT Image 2.5 | — | beginner |
| S | WaveSpeedAI | Runtimes & APIs | Cloud | via GPT Image 2.5 | — | intermediate |
| A | Google | Models | Cloud | 1,174 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.03/image | — |
| A | xAI | Models | Cloud | 1,167 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.04/image | — |
| A | Microsoft AI | Models | Cloud | 1,166 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.04/image | — |
| A | Meta | Models | Cloud | 1,127 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.01/image | — |
| A | Adobe | Apps | Cloud | via Nano Banana 2.1 | $9.99/mo | beginner |
| A | FLORA | Workflow platforms | Cloud | via Nano Banana 2.1 | Free tier · $18/mo | intermediate |
| A | Flow Google | Apps | Cloud | via Nano Banana 2.1 | — | beginner |
| A | Google | Apps | Cloud | via Nano Banana 2.1 | Free tier · $4.99/mo | beginner |
| A | MiniMax | Apps | Cloud | via Nano Banana 2.1 | — | beginner |
| A | Lightricks | Apps | Cloud | via Nano Banana 2.1 | Free tier · $15/mo | beginner |
| A | Luma AI | Apps | Cloud | via Nano Banana 2.1 | Free tier · $30/mo | beginner |
| A | Freepik Company | Apps + Workflow platforms | Cloud | via Nano Banana 2.1 | $20/mo | beginner |
| A | Pika Labs | Apps | Cloud | via Nano Banana 2.1 | Free tier · $10/mo | beginner |
| A | Runway | Apps | Cloud | via Nano Banana 2.1 | Free tier · $15/mo | beginner |
| A | Figma | Workflow platforms | Cloud | via Grok Imagine Image 2.0 | Free tier · $24/mo | intermediate |
| A | SpaceXSI (formerly xAI) | Apps | Cloud | via Grok Imagine Image 2.0 | Free tier · $8/mo | beginner |
| A | Meta | Apps | Cloud | via Muse Image | Free tier | beginner |
| A | Runware | Runtimes & APIs | Cloud | via Muse Image | — | intermediate |
| B | Microsoft AI | Models | Cloud | 1,119 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.02/image | — |
| B | Black Forest Labs | Models | Cloud | 1,116 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.05/image | — |
| B | Google | Models | Cloud | 1,115 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.13/image | — |
| B | Google | Models | Cloud | 1,106 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.03/image | — |
| B | ByteDance Seed | Models | Cloud | 1,100 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.09/image | — |
| B | Reve | Models | Cloud | 1,302 on LMArena Text-to-Image Arena | — | — |
| B | Alibaba (Qwen) | Models | Cloud | 1,094 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.04/image | — |
| B | Alibaba (Qwen) | Models | Local | 1,042 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| B | Dzine | Apps | Cloud | via Nano Banana Pro (Gemini 3 Pro Image) | $8.99/mo | beginner |
| B | Reve | Apps | Cloud | via Reve 2.1 | — | beginner |
| B | Comfy Org | Workflow platforms | Local | via Qwen-Image-2.1 Cloud models: tier S | Free | advanced |
| B | Hugging Face | Runtimes & APIs | Local | via Qwen-Image-2.1 | Free | advanced |
| B | Invoke (open-source community) | Apps + Workflow platforms | Local | via Qwen-Image-2.1 Cloud models: tier S | Free | intermediate |
| B | deepbeepmeep (community project) | Apps | Local | via Qwen-Image-2.1 | Free | intermediate |
| B | leejet (community) | Runtimes & APIs | Local | via Qwen-Image-2.1 | Free | advanced |
| B | SD.Next vladmandic (community) | Apps | Local | via Qwen-Image-2.1 | Free | intermediate |
| B | Haoming02 (community) | Apps | Local | via Qwen-Image-2.1 | Free | intermediate |
| B | TensorStack | Apps | Local | via Qwen-Image-2.1 | Free | beginner |
| B | RunComfy | Workflow platforms | Cloud | via Qwen-Image-2.1 | — | advanced |
| B | ThinkDiffusion | Workflow platforms | Cloud | via Qwen-Image-2.1 | — | advanced |
| C | Krea | Models | Cloud | 1,034 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.03/image | — |
| C | Ideogram | Models | Local | 1,026 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| C | Recraft | Models | Cloud | 1,025 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.04/image | — |
| C | Uni-1.1 Luma AI | Models | Cloud | 1,022 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.04/image | — |
| C | Ideogram | Models | Cloud | 1,016 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.1/image | — |
| C | ByteDance Seed | Models | Cloud | 1,016 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.04/image | — |
| C | Black Forest Labs | Models | Local | 1,000 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | ~24 GB VRAM | — |
| C | inclusionAI (Ant Group) | Models | Local | 999 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| C | Pruna AI | Models | Cloud | 995 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.01/image | — |
| C | NVIDIA | Models | Local | 992 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| C | Tencent | Models | Local | 989 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| C | Alibaba | Models | Cloud | 985 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.03/image | — |
| C | HiDream.ai | Models | Local | 974 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| C | Alibaba (Tongyi-MAI) | Models | Local | 934 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | ~16 GB VRAM | — |
| C | Kuaishou (Kling AI) | Models | Cloud | 918 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | $0.03/image | — |
| C | Baidu | Models | Local | 914 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | ~24 GB VRAM | — |
| C | Krea | Models | Local | 1,113 on LMArena Text-to-Image Arena | Open weights | — |
| C | Z.ai | Models | Local | 888 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| C | Meituan (LongCat) | Models | Local | 858 on Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) | Open weights | — |
| C | Stability AI | Models | Local | 938 on LMArena Text-to-Image Arena | Open weights | — |
| C | Ideogram | Apps | Cloud | via Ideogram 4.0 | Free tier · $20/mo | beginner |
| C | Recraft | Apps | Cloud | via Recraft V4.1 | Free tier | beginner |
| C | Easy Diffusion Easy Diffusion (community) | Apps | Local | via FLUX.2 [dev] | Free | beginner |
| C | mcmonkeyprojects | Apps + Workflow platforms | Local | via FLUX.2 [dev] | Free | intermediate |
| C | Civitai | Apps | Cloud | via FLUX.2 [dev] | Free tier · $10/mo | intermediate |
| C | Acly (Interstice) | Apps | Local | via Z-Image Turbo | Free | intermediate |
| C | Kuaishou | Apps | Cloud | via Kling IMAGE 3.0 Omni | Free tier | beginner |
| C | Mochi Diffusion (community) | Apps | Local | via Stable Diffusion 3.5 Large | Free | beginner |
| C | rupeshs (community) | Apps | Local | via Stable Diffusion 3.5 Large | Free | intermediate |
| C | Artbreeder | Apps | Cloud | via Stable Diffusion 3.5 Large | $7.49/mo | beginner |
| – | vladmandic (community project) | Apps | Local | No public result yet | Free | intermediate |
| – | Draw Things | Apps | Local | No public result yet | Free | intermediate |
| – | Black Forest Labs | Models | Local | No public result yet | ~25 GB VRAM | — |
| – | Microsoft Copilot Microsoft | Apps | Cloud | No public result yet | Free tier · $9.99/mo | beginner |
| – | Midjourney | Apps | Cloud | No public result yet | $10/mo | beginner |
| – | Midjourney | Models | Cloud | No public result yet | — | — |
| – | OpenMOSS | Models | Local | No public result yet | Open weights | — |
| – | Anlatan | Apps | Cloud | No public result yet | $10/mo | beginner |
| – | PixAI | Apps | Cloud | No public result yet | Free tier | beginner |
| – | Pixlr (Inmagine) | Apps | Cloud | No public result yet | $2.49/mo | beginner |
| – | Higgsfield | Models | Cloud | No public result yet | — | — |
| – | ShengShu Technology | Apps | Cloud | No public result yet | Free tier | beginner |
| – | Alibaba | Apps | Cloud | No public result yet | — | beginner |
| – | Alibaba | Models | Cloud | No public result yet | $0.07/image | — |
Benchmarks used
- Artificial Analysis Text to Image Arena (AA-Image-T2I v2.1) by Artificial Analysis (blind human votes, Elo from pairwise human preference (FLUX.2 [dev] anchored at 1000)) · snapshot 19 Oct 2026104 entries (102 ranked, 2 unranked) on the AA-Image-T2I v2.1 overall view. Krea entries are Krea 2 Large (rank 22, 1034), Krea 2 Medium Turbo (34, 1019), Krea 2 Medium (40, 1012); Krea 3 (released 2026-10-15) is not listed as of 2026-10-19. No last-updated date shown, so as_of = retrieval date.
- LMArena Text-to-Image Arena by LMArena (arena.ai) (blind human votes, Arena score (Bradley-Terry rating from pairwise human votes)) · snapshot 7 Oct 2026Read from LMArena's official HF dataset lmarena-ai/leaderboard-dataset (text_to_image/latest, overall, published 2026-10-07) because arena.ai returns 403 to scripted fetches; values rounded to integers. Covers the current API leaders (GPT Image 2.5, Grok Imagine 2.0, MAI-Image-2.6, Nano Banana 2.1, Reve 2.1, Muse Image) and main open models. Missing: Midjourney, FLUX 3 Image, FLUX 3 Image Klein, Ideogram 4.5 (edit arena only).