All vikis
007 First Light
Aion 2
Ananta
ARC Raiders
ArcheAge Chronicles
Call of Duty: Modern Warfare 4
ChatGPT
Chrono Odyssey
Civilization 3
Civilization 4
Claude
Crimson Desert
Deadlock
Diablo 4
Diablo 5
Enshrouded
Fable
Final Fantasy Resonance
Football Manager 27
Forza Horizon 6
God of War
Grand Theft Auto 6
Heroes of Might and Magic 3Flux
Flux is the family of image (and now video) models from Black Forest Labs, some with open weights you can run yourself. The newest open image model, Flux 3 Image Klein (Oct 15, 2026), is free for commercial use under $5 million in revenue, and the API starts at $0.009 an image.
Flux is a family of AI image models from Black Forest Labs, a lab in Freiburg, Germany and San Francisco whose founders helped create Latent Diffusion and Stable Diffusion, sold through a pay-per-image API and also released as open weights you can run on your own computer; the newest is the Flux 3 generation, whose open Flux 3 Image Klein came out on Oct 15, 2026, and API prices start at $0.009 for a 1K image (as of Nov 6, 2026). There are no subscriptions: Black Forest Labs charges per image, and many other apps run Flux under the hood.
Pick Flux when you want to run an image model locally or fine-tune it on your own style or product (with ComfyUI or Diffusers), or want a cheap, fast API with editing by reference images. Pick something else when you want a polished consumer app with no setup (Midjourney, GPT Image in ChatGPT or Nano Banana in Gemini), or the highest blind-vote scores: in Nov 2026 Flux's best entry ranked well below OpenAI's and Google's on Arena. For local tools see Stable Diffusion and Run AI Locally; for the field, Best AI Image Generator.
Quick facts
| Maker | Black Forest Labs (Freiburg and San Francisco) |
| Launched | FLUX.1 in 2024; FLUX.2 Nov 25, 2025; FLUX 3 Jul 23, 2026 |
| Latest image models | Flux 3 Image (API) and Flux 3 Image Klein (open) |
| Get it | BFL API, Hugging Face weights, and partner apps |
| Price | API from $0.009 an image (Flux 3 Image Klein, 1K) (as of Nov 6, 2026); no subscription |
| Open weights | Yes for some: Apache 2.0 (FLUX.1 schnell, FLUX.2 klein 4B), non-commercial (FLUX.2 dev), Kommunity License (Flux 3 Image Klein) |
| Best for | Self-hosting, fine-tuning, multi-reference editing, cheap API images |
Models and licenses
| Model | Released | Weights | License |
|---|---|---|---|
| FLUX.1 [schnell] | 2024 | Open, 12B | Apache 2.0, commercial use allowed |
| FLUX.1 Kontext [pro] / [max] / [dev] | May 29, 2025 | [dev] open, 12B | API for pro and max |
| FLUX.2 [pro] / [flex] / [max] | Nov 25, 2025 | API only | Paid API |
| FLUX.2 [dev] | Nov 25, 2025 | Open, 32B | FLUX Non-Commercial License; commercial self-hosting needs a paid license |
| FLUX.2 [klein] 4B | After Nov 2025 | Open, 4B | Apache 2.0, runs in about 13 GB of VRAM |
| Flux 3 Image | 2026 | API only | Paid API |
| Flux 3 Image Klein | Oct 15, 2026 | Open, 5.6B | FLUX Kommunity License: free commercial use under $5M annual revenue |
Sources: BFL models, FLUX.2 post, Kontext post, Flux 3 Image Klein post and the Hugging Face model cards, read Nov 6, 2026. Companies above the free limits buy a self-hosting license (Builder, Platform, Professional or Enterprise; prices are not published).
API prices
| Model | Price (as of Nov 6, 2026) |
|---|---|
| Flux 3 Image | $0.048 (1K) to $0.607 (4K) an image |
| Flux 3 Image Klein | $0.009 (1K) to $0.036 (4K) an image |
| FLUX.2 [max] | $0.07 for the first megapixel, $0.03 each after |
| FLUX.2 [pro] | $0.03 for the first megapixel, $0.015 each after |
| FLUX.1 Kontext [pro] | $0.04 an image |
Source: Black Forest Labs pricing. Video from Flux 3 Video costs $0.15 to $0.41 a second.
Features
Open weights you can run. Flux 3 Image Klein runs on NVIDIA GeForce RTX cards with 8 GB of VRAM in its INT8 build, through ComfyUI or Diffusers, and Black Forest Labs reports about 4 seconds for a 1-megapixel image on an RTX 5090. A base version is published for fine-tuning, and LoRA training was supported from day one.
Editing with references. Kontext (May 2025) was built to edit an image from text plus the image itself. FLUX.2 takes up to 10 reference images and edits at up to 4 megapixels, and Flux 3 Image adds bounding boxes to place elements or confine an edit to one area, with native 4K.
Text and layouts. Black Forest Labs says FLUX.2 renders complex text, infographics and interface mock-ups reliably, and Flux 3 adds multilingual text rendering.
Beyond images. Flux 3, announced on Jul 23, 2026, is one model trained on images, video and audio. Flux 3 Video makes clips up to 20 seconds with sound, and Flux 3 Action predicts robot movements; see Best AI Video Generator for video rivals.
Flux vs the alternatives
On the Arena text-to-image leaderboard (updated Nov 2, 2026, read Nov 6), FLUX.2 [max] scored 1161, around 30th, against 1427 for OpenAI's top GPT Image entry; Flux 3 Image was not yet listed.
- Stable Diffusion: Stability AI's older open models, with years of community add-ons and lighter hardware needs for SDXL.
- GPT Image and Nano Banana: higher Arena scores and free consumer apps, but no weights.
- Qwen: Alibaba's Qwen-Image line, whose Qwen-Image-3.0-Pro scored 1254 on the same Arena board.
- Krea: a creative app with many partner models and real-time drawing, with no local setup.
- Midjourney: a subscription app with a stronger default style and no API.
Frequently asked questions
Is Flux free? Some Flux models are free to download and run yourself: FLUX.1 schnell and FLUX.2 klein 4B under Apache 2.0, and Flux 3 Image Klein free for commercial use by those under $5 million in annual revenue; Black Forest Labs' own API charges per image.
Can I use Flux commercially? Yes for the Apache 2.0 models and for Flux 3 Image Klein below the revenue limit; FLUX.2 dev is non-commercial for self-hosting unless you buy a license, and images made through the paid Flux API can be used commercially.
What is Flux Kontext? FLUX.1 Kontext is Black Forest Labs' May 2025 model family for editing an image with text instructions, in pro, max and open dev versions; FLUX.2 and Flux 3 have since added editing with several reference images.
What is the latest Flux model? As of Nov 6, 2026 the latest Flux image models are Flux 3 Image (API) and Flux 3 Image Klein, an open 5.6-billion-parameter model released on Oct 15, 2026.
Can Flux run on my computer? Yes. Flux 3 Image Klein runs on NVIDIA RTX graphics cards with as little as 8 GB of VRAM in its INT8 build, using ComfyUI or Diffusers.
Sources
- Models, Black Forest Labs, read Nov 6, 2026
- Pricing, Black Forest Labs, read Nov 6, 2026
- Licensing, Black Forest Labs, read Nov 6, 2026
- FLUX 3 Image Klein, Black Forest Labs, Oct 15, 2026
- FLUX 3 - Real World Models, Black Forest Labs, Jul 23, 2026
- FLUX.2, Black Forest Labs, Nov 25, 2025
- FLUX.1 Kontext, Black Forest Labs, May 29, 2025
- FLUX.1 schnell, FLUX.2 dev and FLUX.2 klein 4B model cards, Hugging Face, read Nov 6, 2026
- Text-to-Image leaderboard, Arena, read Nov 6, 2026
- Introducing FLUX 3, Black Forest Labs, Aug 4, 2026 (video)
- FLUX 3 Is Here - Everything You NEED to Know, ElevenLabs, Aug 12, 2026 (video)
Moments
Introducing FLUX 3
Black Forest Labs
FLUX 3 Is Here - Everything You NEED to Know
ElevenLabs
Photos
Related
-
Adobe FireflyAdobe Firefly is Adobe's AI app for images, video and audio, with its own Firefly models (trained, Adobe says, on licensed and public domain content) and partner models from Google, OpenAI and others. It has free daily generations, and paid plans start at $9.99 a month.
-
- ImagenImagen is Google's older line of text-to-image models, last Imagen 4 (2025). Google now calls it legacy: the Gemini API shut its Imagen models down from Aug 17, 2026 and points developers to Nano Banana instead.
-
KreaKrea is an AI creative app that generates images in real time as you type or draw, runs its own Krea 3 editing model and many partner image and video models, and upscales images. It is free with 100 compute units a day, and paid plans cost $9 to $200 a month.
-
Leonardo AILeonardo AI (Leonardo.Ai) is a Canva-owned creative app for AI images and video that offers its own Lucid models plus 80 or more partner models such as Nano Banana, GPT Image and Flux. It is free with 150 tokens a day, and paid plans cost $12 to $60 a month.
-
- SeedreamSeedream is ByteDance's family of image generation and editing models, made by its Seed team. The newest, Seedream 5.0 Pro, adds reasoning, infographics and layer separation, and costs $0.045 an image through BytePlus ModelArk.
-
See also
-
MidjourneyMidjourney is a paid AI image and video generator from the independent lab Midjourney, Inc. Plans run from $10 to $120 a month with no free tier, and its default model since Jul 24, 2026 is V8.2.
-
-
Nano BananaNano Banana is Google's name for its Gemini image generation and editing models. The newest, Nano Banana 2.1, came out on Oct 6, 2026; it is free to use with limits in the Gemini app and costs about $0.034 per 1K image in the Gemini API.
-
Stable DiffusionStable Diffusion is Stability AI's family of open image models (SD 1.5, SDXL, SD 3.5) that anyone can download and run on their own computer. SD 3.5 is free to use commercially for those under $1 million in annual revenue, and Stability's API charges from $0.025 an image.
-
Run AI LocallyTo run AI on your own computer, install Ollama or LM Studio (both free) and download an open model sized to your memory, such as Gemma 4, Qwen 3.5 or 3.8, or gpt-oss 20b. With 8 to 16 GB a small model runs well; a 24 GB graphics card or a 32 GB Mac runs 27B to 31B models.
-
Best AI Image GeneratorThe best AI image generator in Nov 2026, by both LMArena and Artificial Analysis votes, is OpenAI's GPT Image 2.5 in ChatGPT, with Google's Nano Banana 2.1, Microsoft's MAI-Image-2.6 and SpaceXAI's Grok Imagine close behind. Adobe Firefly is the pick for commercially safe work and Flux for open weights.