FLUX.2 [max]
Top-tier hosted model in the FLUX.2 family, exposed as the /flux-2-max endpoint on the BFL API.
- Resolution
- 4 MP for image editing (FLUX.2 family, per BFL launch post); exact max width/height not published
- Weights
- Not released
- API
- Yes
- Commercial use
- Vendor states commercial use is permitted
Handles text-to-image plus single- and multi-reference editing in one model, with the FLUX.2 line documented for editing at up to 4 megapixels and up to 10 simultaneous reference images. Priced by output megapixel rather than a flat per-image rate.
Commercial use is via BFL API service terms; no separate model license is required for API output.
Specification
- What it takes in
- text, image
- What it makes
- image
- Maximum resolution
- 4 MP for image editing (FLUX.2 family, per BFL launch post); exact max width/height not published
- Aspect ratios
- not established
- Controls
- image-to-image, reference-character-consistency, style-reference, text-rendering, editing-by-instruction, inpainting
- Weights
- Not released
- API
- Yes
- Pricing
- per image, from $0.07 (scales with output resolution / megapixels)
- Released or updated
- 2025-12
Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.
Strengths
- Highest-quality tier of the FLUX.2 family
- Multi-reference editing (up to 10 images) in the same checkpoint as generation
- Strong legible typography, infographics and UI mockups per vendor claims
Weaknesses
- Most expensive FLUX endpoint
- Megapixel-based pricing makes per-image cost non-obvious
- No published hard resolution ceiling
Best for
- Highest-fidelity hero images and multi-reference compositing where cost per image is secondary.
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- Release month for [max] comes from the Wikipedia FLUX variant table (December 2025); no BFL launch post for [max] was reachable (bfl.ai/blog/flux-2-max returned 404).
- A third-party breakdown describes the megapixel model as $0.07 for the first output megapixel plus $0.03 per additional input megapixel; BFL docs only publish 'from $0.07' and point to a calculator.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
MCP servers that front Black Forest Labs
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
Adclip
Ad creative generation via MCP, copy and static images from a JSON brief. Keyless.
-
BananaBanana Image & Video Generation
Generate images & video (Nano Banana, Veo, Omni) pay-as-you-go. No subscription, crypto payments.
-
Civitai
Civitai MCP.
-
Clipia
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
-
Cochlea
Render, analyze, and verify audio (WAV/FLAC/mp3/ogg) offline and deterministically via MCP tools.
-
ComfyUI Builder
ComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
FLUX.1 Kontext [pro] / [max]
Instruction-driven image editing models from the FLUX.1 generation (2025), still exposed as live /flux-kontext-pro and /flux-kontext-max endpoints. Th
Image generation
FLUX.2 [dev]
32-billion-parameter open-weights checkpoint that does text-to-image plus single- and multi-reference editing in one model, released 25 November 2025
Image generation
FLUX.2 [flex]
Hosted FLUX.2 variant that exposes sampling steps and guidance scale as API parameters, letting callers trade quality and prompt adherence against spe
Image generation