NVIDIA and Black Forest Labs Redefine Image Editing With Flux.1 Kontext Dev and TensorRT

Black Forest Labs - one of the world's leading AI research labs - are changing the game for AI image generation, with their new FLUX. 1 Kontext model introducing new ways for users to guide and refine the image generation process.

While traditionally the refining process for AI-generated images involves combinations of models and guiding ControlNets, the new FLUX model simplifies this by providing a single model that can handle both image generation and editing through natural language.

NVIDIA has collaborated with Black Forest Labs to optimise FLUX.1 Kontext [dev] for NVIDIA RTX GPUs using the NVIDIA TensorRT software development kit and quantisation to deliver faster inference with lower VRAM requirements.

Providing Kontext
Black Forest Lab's FLUX.1 image models have earned global attention for delivering high-quality visuals with exceptional prompt adherence. Now, with its new FLUX.1 Kontext model, the lab is fundamentally changing how users can guide and refine the image generation process.

These models allow users to start from a reference image and guide edits with simple language, without the need for fine-tuning or complex workflows with multiple ControlNets. Because the model accepts both text and image inputs, users can easily reference a visual concept and guide how it evolves naturally and intuitively. This enables coherent, high-quality image edits that stay true to the original concept.

FLUX.1 Kontext's key capabilities include:
Character Consistency: Preserve unique traits across multiple scenes and angles.
Localised Editing: Modify specific elements without altering the rest of the image.
Style Transfer: Apply the look and feel of a reference image to new scenes.
Real-Time Performance: Low-latency generation supports fast iteration and feedback.

Optimising for RTX
To further streamline workflows and broaden accessibility, NVIDIA and Black Forest Labs collaborated to quantise the model - reducing the VRAM requirements so more people can run it locally - and optimised it with TensorRT to double its performance. Thanks to TensorRT - a framework to access the Tensor Cores in NVIDIA RTX GPUs for maximum performance - users gain access to over 2x acceleration compared with running the original BF16 model with PyTorch.

FLUX.1 Kontext [dev] is available to try on Hugging Face (Torch and TensorRT). AI enthusiasts interested in testing these models can download the Torch variants and use them in ComfyUI. Black Forest Labs has also made available an online playground for testing the model. For advanced users and developers, NVIDIA is working on sample code for easy integration of TensorRT pipelines into workflows. Check out the DemoDiffusion repository to come later this month.

For further news covering NVIDIA's various AI products and services, check out the NVIDIA AI Garage blog. In addition, NVIDIA's Plug and Play: Project G-Assist Plug-In Hackathon - running virtually through Wednesday, July 16 - is inviting developers to explore AI and build custom G-Assist plug-ins for a chance to win prizes.

Swipe Right
4th Floor, 129 Oxford Street, London, W1D 2HZ
Elijah Laino
elijah@swiperight.gg

Each week, the RTX AI Garage blog series features community-driven AI innovations and content for those looking to learn more about NVIDIA NIM microservices and AI Blueprints, as well as building AI agents, creative workflows, digital humans, productivity apps and more on AI PCs and workstations.

This release was published on openPR.