Black Forest Labs' general-purpose text-to-image model, also runs locally via Wan2GP.
Model Category
Text-to-Image Models — 70+ Ways to Generate an Image From a Prompt
From fast turbo diffusion to flagship names like Nano Banana 2 and Midjourney v7 — Open Generative AI's text-to-image category runs 70+ models with no content filters and no subscription.
70+ Text-to-Image Models$0 Cost to Generate
Text-to-image is the entry point of the Image Studio: type a prompt, pick a model, and get a finished image with no reference photo required. It's the largest single text-to-image category in the catalog at 70+ models, spanning fast turbo diffusion models to flagship names like Nano Banana 2 and Midjourney v7.
Text-to-Image Models
70+ Text-to-Image Models, One Open Generative AI Catalog
Every text-to-image model below runs through the same Image Studio prompt box — no separate accounts, no separate pricing, no filters swapped in per model.
Google Gemini 3.1 Flash Image — 1K/2K/4K resolution with Google Search enhancement.
ByteDance — basic/high quality, 8 aspect ratios, up to 4K output.
Strong at rendering readable text inside a generated image.
Stylised, art-directed image generation.
OpenAI's image generation model, included in the catalog.
Open weights, high-resolution generation — also bundled for local sd.cpp inference.
MiniMax — 8 aspect ratios, up to 4 images per request, 1500-character prompts.
Hosted vs. run it locally
Generate in the Cloud, or on Your Own GPU
Open Generative AI ships the same text-to-image catalog two ways — a hosted app with zero setup, and a desktop app that can run image generation entirely on your own machine.
Hosted
The hosted app runs the full 70+ text-to-image catalog — Flux Dev, Nano Banana 2, Seedream 5.0, Ideogram v3, Midjourney v7, GPT-4o and more — through the MuAPI gateway, no GPU or setup required.
Run It Locally
The desktop app's bundled sd.cpp engine generates locally with Z-Image Turbo, Z-Image Base, Dreamshaper 8, Realistic Vision v5.1, Anything v5 and SDXL Base on Metal, CUDA, Vulkan or ROCm — no API key needed.
Compare
Three Text-to-Image Models, Side by Side
A quick look at three representative models in the catalog — pick the one that matches what you're building.
| Model | Provider / Source | What it's built for |
|---|---|---|
| Flux Dev | Black Forest Labs | General-purpose text-to-image, also runs locally via Wan2GP |
| Nano Banana 2 | Google Gemini 3.1 Flash Image | 1K/2K/4K resolution with Google Search enhancement |
| Seedream 5.0 | ByteDance | 8 aspect ratios, basic/high quality, up to 4K output |
Swipe to see the full table
FAQ
Text-to-Image Model FAQ
70+, including Flux Dev, Nano Banana 2, Seedream 5.0, Ideogram v3, Midjourney v7, GPT-4o and SDXL — the model set the Image Studio uses whenever no reference image is attached.
Explore more
More Open Generative AI Model Categories
Text-to-image pairs closely with the categories below, plus the Image Studio page that runs it end to end.
Generate an Image With Open Generative AI — Free, Right Now
70+ text-to-image models, no content filters, no subscription. No account required to try it.
Try Free