{"id":4073,"date":"2025-07-24T13:41:59","date_gmt":"2025-07-24T13:41:59","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2025\/07\/24\/creative-agency-black-mixture-creates-stunning-visuals-with-generative-ai-powered-by-nvidia-rtx\/"},"modified":"2025-07-24T13:41:59","modified_gmt":"2025-07-24T13:41:59","slug":"creative-agency-black-mixture-creates-stunning-visuals-with-generative-ai-powered-by-nvidia-rtx","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2025\/07\/24\/creative-agency-black-mixture-creates-stunning-visuals-with-generative-ai-powered-by-nvidia-rtx\/","title":{"rendered":"Creative Agency Black Mixture Creates Stunning Visuals With Generative AI Powered by NVIDIA RTX"},"content":{"rendered":"
\n\t\t<\/span> <\/span> <\/span><\/span><\/p>\n

For media company Black Mixture, AI isn\u2019t just a tool \u2014 it\u2019s an entire pipeline to help bring creative visions to life.<\/p>\n

Founded in 2010 by Nate and Chriselle Dwarika, Black Mixture<\/a> takes an innovative approach to using AI in creative workflows. It built its visual reputation in motion design and production using traditional artistry methods and has since expanded its breadth of work to educating artists who want to start incorporating AI tools into their own projects, curating custom AI resources<\/a> and sharing tutorials on their YouTube<\/a> channel.<\/p>\n

In recent years, Black Mixture has enhanced its creative workflows in apps with GPU-accelerated features. Today, the company has added new AI models and features to its toolkit, running the most complex AI tasks locally on an NVIDIA GeForce RTX 4090-equipped system.<\/p>\n<\/p>\n

Black Mixture uses generative AI<\/a> to create or enhance video footage and image assets. This week, RTX AI Garage<\/a> dives into some of the apps and workflows the company uses, as well as some AI tips and tricks.<\/p>\n

Plus, NVIDIA Broadcast<\/a> version 2.0.2 is now available, with up to a 15% performance boost for GeForce RTX 50 Series and NVIDIA RTX PRO Blackwell GPUs.<\/p>\n

An AI for Presentation<\/b><\/h2>\n

Iteration is a critical part of the generative AI content creation process, with a typical project requiring the generation of up to hundreds of images.<\/p>\n

While models such as ChatGPT and Google Gemini can create a single image fairly quickly, artists like Nate and Chriselle Dwarika require much faster speeds and greater creative control. With on-device AI tools accelerated by RTX, that speed and control is achievable.<\/p>\n

\"\"<\/a>
Nearly all locally powered generative AI models are accelerated by NVIDIA GeForce RTX.<\/figcaption><\/figure>\n
\n

Generating a standard 1024\u00d71024 image in ComfyUI takes 2-3 seconds on my RTX 4090. When you\u2019re batch-generating hundreds of assets, that\u2019s the difference between an hour, an entire day or more.<\/i>\u201d \u2014 Nate Dwarika<\/p>\n<\/div>\n

Using generative AI, the Black Mixture team can easily draw inspiration from a much wider variety of high-quality images than with manual methods, while refining outputs to their client\u2019s preferred vision.<\/p>\n

Nate Dwarika uses the node-based interface ComfyUI<\/a> in his text-to-image workflow. It offers a high degree of flexibility in the arrangement of nodes, with the ability to combine different characteristics of popular generative AI models \u2014 all accelerated by his GeForce RTX GPU.<\/p>\n

One such generative AI model is FLUX.1-dev, an image generation model from Black Forest Labs. When deployed in ComfyUI on an RTX AI PC, the model taps CUDA accelerations in PyTorch that significantly speeds an artist\u2019s workflow. The image below, which would take about two minutes per image on a Mac M3 Ultra, takes less than 12 seconds to generate with a GeForce RTX 4090 desktop GPU.<\/p>\n

\"\"<\/a>
Made in seconds, not minutes, on RTX.<\/figcaption><\/figure>\n

Black Forest Labs also offers FLUX.1 Kontext<\/a>, a family of models that allow users to start from a reference image or text prompt and guide edits with suggestions, without fine-tuning or complex workflows with multiple ControlNets, extensions that enable more precise control over the image structure, composition and more.<\/p>\n

Take the stunning dragon visual below. FLUX.1 Kontext enabled the artist to rapidly iterate on his initial visual, guiding the AI model with additional inputs like poses, edges and depth maps within the same prompt window.<\/p>\n

\"\"<\/a>
You\u2019re scared. I\u2019m not scared.<\/figcaption><\/figure>\n

FLUX.1 Kontext is also offered in quantized variants that reduces VRAM requirements so more users can run it locally. It makes use of hardware accelerations in NVIDIA GeForce RTX Ada Generation and Blackwell GPUs.<\/p>\n

Together with NVIDIA TensorRT<\/a> optimizations, these variants provide more than double the performance. There are two levels of quantization: FP8 and FP4. FP8 is accelerated on both GeForce RTX 40 and 50 Series GPUs, while FP4 is accelerated solely on the 50 Series.<\/p>\n

Dwarika also uses Stable Diffusion 3.5, which supports FP8 quantization for the GeForce RTX 40 Series \u2014 enabling 40% less VRAM usage and nearly doubling image generation speed.<\/p>\n<\/p>\n

With these visual AI tools, Black Mixture can create photorealistic, original visuals for its clients in a time- and cost-effective way.<\/p>\n

Nate and Chriselle Dwarika also use a variety of more traditional content creation tools \u2014 all accelerated by RTX. For video content, Nate Dwarika captures footage on OBS Studio using the NVIDIA encoder (NVENC<\/a>) built into his GeForce RTX 4090 GPU. Because NVENC is a separate encoder, the rest of the GPU can focus on resource-intensive ComfyUI workflows without reducing performance, all while maintaining top encoding quality.<\/p>\n

The husband-and-wife duo completes final edits and touch-ups in Adobe Premiere Pro, which includes a wide variety of RTX-accelerated AI features like Media Intelligence, Enhance Speech and Unsharp Mask. They use GPU-accelerated encoding with NVENC to dramatically speed final file exports.<\/p>\n<\/p>\n

Black Mixture\u2019s next project is an Advanced Generative AI Course<\/a> to help creators get started with using AI in their workflows. It includes a series of live trainings that explore generative AI capabilities, as well as NVIDIA RTX AI technology and optimizations. Attendees can expect 6-8 weeks of live sessions, 30+ hours of self-paced lessons, guest experts, a student showcase, exclusive AI toolkits and more.<\/p>\n

Next-Generation Streaming<\/b><\/h2>\n

NVIDIA Broadcast version 2.0.2 delivers 15% faster performance for NVIDIA GeForce RTX 50 Series and NVIDIA RTX PRO Blackwell GPUs.<\/p>\n

With the performance boost, AI features like Studio Voice and Virtual Key Light can now be used on GeForce RTX 5070 GPUs or higher. Studio Voice enhances the sound of a user\u2019s microphone to match that of a high-quality microphone, while Virtual Key Light relights a subject\u2019s face to illuminate it as if it were well-lit by two lights.<\/p>\n

The Eye Contact feature \u2014 which uses AI to make it appear as if users are looking directly at the camera, even when glancing to the side or taking notes \u2014 is improved with increased stability for eye color. Additional enhancements include updated user interface elements for easier navigation and improved high contrast theme support.<\/p>\n<\/p>\n

Download NVIDIA Broadcast<\/a>.<\/p>\n

Each week, the <\/i>RTX AI Garage<\/i><\/a> 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 <\/i>AI agents<\/i><\/a>, creative workflows, productivity apps and more on AI PCs and workstations.\u00a0<\/i><\/p>\n

Plug in to NVIDIA AI PC on <\/i>Facebook<\/i><\/a>, <\/i>Instagram<\/i><\/a>, <\/i>TikTok<\/i><\/a> and <\/i>X<\/i><\/a> \u2014 and stay informed by subscribing to the <\/i>RTX AI PC newsletter<\/i><\/a>. Join NVIDIA\u2019s <\/i>Discord server<\/i><\/a> to connect with community developers and AI enthusiasts for discussions on what\u2019s possible with RTX AI.<\/i><\/p>\n

Follow NVIDIA Workstation on <\/i>LinkedIn<\/i><\/a> and <\/i>X<\/i><\/a>.\u00a0<\/i><\/p>\n

See <\/i>notice<\/i><\/a> regarding software product information.<\/i><\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/rtx-ai-garage-black-mixture-flux-stable-diffusion-broadcast\/<\/p>\n","protected":false},"author":0,"featured_media":4074,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/4073"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=4073"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/4073\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/4074"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=4073"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=4073"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=4073"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}