FLUX.2-dev

About

What FLUX.2-dev is

This is a GGUF quantized version of FLUX.2-dev. unsloth/FLUX.2-dev-GGUF uses Unsloth Dynamic 2.0 methodology for SOTA performance. Important layers are upcasted to higher precision. Samples FLUX.2 [dev] is a 32 billion parameter rectified flow transformer capable of generating, editing and combining images based on text instructions. For more information, please read our blog post. Key Features 1. State of the art in open text-to-image generation, single-reference editing and multi-reference editing. 2. No need for finetuning: character, object and style reference without additional training in one model. 4. Trained using guidance distillation, making FLUX.2 [dev] more efficient. 5. Open weights to drive new scientific research, and empower artists to develop innovative workflows. 6. Generated outputs can be used for personal, scientific, and commercial purposes, as described in the [FLUX \[dev\] Non-Commercial License](https://github.com/black-forest-labs/flux/blob/main/modellicenses/LICENSE-FLUX1-dev). Usage We provide a reference implementation of FLUX.2 [dev], as well as sampling code, in a dedicated github repository. Developers and creatives looking to build on top of FLUX.2 [dev] are encouraged to use this as a starting point. FLUX.2 [dev] is also available in both ComfyUI and Diffusers. Using with diffusers 🧨 For local deployment on a consumer type graphics card, like an RTX 4090 or an RTX 5090, please see the diffusers docs on our GitHub page. As an example, here's a way to load a 4-bit quantized model with a remote text-encoder on an RTX 4090: Risks Black Forest Labs is committed to the responsible development and deployment of our models. Prior to releasing the FLUX.2 family of models, we evaluated and mitigated a number of risks in our model checkpoints and hosted services, including the generation of unlawful content such as child sexual abuse material (CSAM) and nonconsensual intimate imagery (NCII). We implemented a series of pre-release mitigations to help prevent misuse by third parties, with additional post-release mitigations to help address residual risks: 1. Pre-training mitigation. We filtered pre-training data for multiple categories of “n

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How image models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys unsloth-flux-2-dev for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (unsloth-flux-2-dev below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/images/generations \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"unsloth-flux-2-dev","prompt":"a red bicycle","size":"1024x1024"}'

Details

Languages, data & research

Licence

Commercial licence needed

Sources

Weights & code

Explore

More image models