Skip to main content
aifeatures.ai
⬛

FLUX

by Black Forest Labs

8M / mo
100% Free
Try FLUX (opens in a new tab)

FLUX is an image generation model built by Black Forest Labs, a team founded by former Stable Diffusion researchers. It's become the default open-weight option for people who want Midjourney-level image quality without depending on a closed API, with strong prompt adherence and noticeably better hands and text rendering than earlier open models. Developers self-host it, fine-tune it on custom styles, or run it through hosted endpoints on platforms like Replicate and Hugging Face.

FLUX features and capabilities, including which plan they need and how they compare in the CanIUse matrix.

black-forest-labsAdded 2026-07-17Catalog rank 9

Used in combinations

See who owns what in this stack

Compare FLUX with:

🖌️ Canva Magic Studio🎨 Figma🎨 Midjourney✨ Adobe Express🔥 Adobe Firefly🌀 Stable Diffusion🖼️ Photoroom🔤 Ideogram✏️ Recraft🖼️ Leonardo.Ai🎨 Krea📢 AdCreative.ai
Looking for a free alternative to FLUX? →

Directory alternatives

Stable DiffusionStability AI's open-source text-to-image modelAdded 2026-07-17image_generationcreativetext_to_imagevisual#8FreeMatrixMidjourneyAI image generator for creating artistic and realistic imagesAdded 2025-09-21designimage_editingcreativevisual#8PaidMatrixDALL-E 3OpenAI's text-to-image model inside ChatGPTAdded 2025-01-01image_generationcreativetext_to_imagevisual#5FreemiumGPT ImageOpenAI's native image generation model built into ChatGPT and the APIAdded 2026-07-17image_generationcreativetext_to_imagevisual#5FreemiumIdeogramAI image generator with best-in-class text renderingAdded 2025-01-01image_generationcreativetext_to_imagevisual#9FreemiumMatrixLeonardo AIProfessional AI image generation for game assets and creative workAdded 2025-01-01image_generationcreativetext_to_imagevisual#8FreemiumMatrixKrea AIReal-time AI image generation and enhancementAdded 2025-01-01image_generationcreativetext_to_imagevisual#8FreemiumCivitaiCommunity hub for Stable Diffusion models, LoRAs, and AI artAdded 2025-09-21image_generationcreativetext_to_imagevisual#8Freemium

✨ Modalities

💬
Text Input
Yes, requires free plan. Text prompts drive FLUX text-to-image on the BFL API and open-weight inference.
🖼️
Image Upload / Vision
Yes, requires plus plan. FLUX.1 Kontext and Fill/Expand endpoints take images for editing. Hosted API is pay-as-you-go.
🎨
Image Generation
Yes, requires free plan. Core product: FLUX.1 [schnell]/[dev] locally, plus FLUX.2 Pro/Max/Flex/Klein via API.
🎙️
Voice Mode
No. Not a conversational voice product. Docs mention synchronized audio on some FLUX 3 video paths; that is generated soundtrack, not a voice loop.
🎥
Video Understanding
No. FLUX 3 docs talk about generating video, not Q&A over uploaded video.
🎬
Video Generation
No. Not a video generation product.
📁
File Upload (PDF, DOCX)
No. Inputs are prompts and images, not PDF/DOCX.
💻
Code Execution
No. You run inference code; the model does not execute your Python.
🔊
Audio Input
No. No audio-file input is documented for image endpoints.
🖌️
Canvas / Artifact Editor
Partial. Kontext/Fill/Expand are image editors via API, not a chat canvas.
🖥️
Screen Sharing / Computer Use
No. No computer-use product.

🧠 Memory & Context

🧠
Persistent Memory
No. Each generation is a job. No user memory layer.
📏
Large Context Window
No. Not an LLM context-window product.
⚙️
Custom Instructions
No. No global instruction profile. Fine-tunes/LoRAs are weights, not a system prompt.
📜
Conversation History
No. Dashboard jobs are not a chat history product.

🔌 Integrations

🌐
Web Search / Browsing
No. Does not browse the live web.
🔌
Plugins / Extensions
Partial. Community hosts FLUX on Replicate/Hugging Face. That is not a BFL plugin marketplace.
🔧
API Access
Yes, requires plus plan. Official async API at api.bfl.ai (plus eu/us regional). Auth is an x-key. Pay-as-you-go, no seat fee.
⚡
Zapier Integration
Unknown. No first-party Zapier app was checked.
🤖
Custom GPTs / Bots
No. No Custom GPT store. Fine-tunes are weights.
👥
Real-time Collaboration
No. No multiplayer editor.
🐦
Live Social Data Integration
No. No live social firehose.
📚
Live Citation Mapping
No. Not a cited-search product.

👨‍💻 Developer

🛠️
Function Calling
No. You POST a generation job and poll. No tool-calling chat.
⚡
Streaming Responses
No. Async poll for the finished image, not token streaming.
🎛️
Fine-Tuning
Yes, requires plus plan. Open-weight [dev]/[klein] plus paid self-host licenses list fine-tuning and LoRA rights. API OpenAPI also lists fine-tune management.
📐
Embeddings API
No. Not an embeddings API.
📋
Structured Output (JSON)
No. Output is an image (jpeg/png/webp), not JSON schema.
🧩
Reasoning / Thinking Mode
No. Not an LLM reasoning mode.
🏠
Local Execution
Yes, requires free plan. Official GitHub inference repo runs open-weight FLUX.1 [schnell] and [dev] on your hardware.
🔓
Open Weights
Yes, requires free plan. FLUX.1 [schnell] is Apache-2.0; [dev] is a non-commercial license. Hosted Pro/Max stay closed.
🤖
Multi-Agent Orchestration
No. Not a multi-agent orchestrator.

📱 Platforms

🌐
Web App
Yes, requires free plan. Docs point at a playground plus the dashboard at dashboard.bfl.ai.
📱
iOS App
No. No official iOS app is documented.
🤖
Android App
No. No official Android app is documented.
🖥️
Desktop App
No. Self-host is your own stack, not a BFL desktop app.
🔵
Chrome Extension
No. No official Chrome extension.

🔒 Privacy

🔒
GDPR Compliant
Partial. api.eu.bfl.ai is documented as the EU/GDPR regional endpoint. That is data routing, not a published DPA we read here.
🚫
Opt Out of Data Training
Unknown. Training use of API prompts was not checked on a privacy policy this round.
🏢
Enterprise Privacy Mode
Yes, requires enterprise plan. Pricing lists Enterprise self-host licensing plus custom volume/SLA. EU and US regional APIs exist.

💼 Workspaces

📂
Projects / Folders
No. No notebook/project product. Dashboard jobs only.