DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

Double exposure is a photography technique that combines multiple images into a single frame, creating a dreamlike and artistic effect. With the advent of AI image generation, we can now create stunning double exposure art in minutes using LoRA models. In this guide, we'll walk through how to use the Flux Double Exposure Magic LoRA from CivitAI with DeepInfra's deployment platform.
Once you navigate to this section, you will see a screen like this:
5. Write your preferred model name.
6. We'll use FLUX Dev for this LoRA. You can keep it as it is.
7. Add the following CivitAI URL: https://civitai.com/models/715497/flux-double-exposure-magic?modelVersionId=859666
8. Click "Upload" button, and that's it. VOILA!
Once LoRA processing has completed, you should navigate to
http://deepinfra.com/<your_name>/<lora_name>
When you have navigated, you should view our classical dashboard, but with your LoRA name.
Now let's create some stunning visuals... Let's break down this stunning example:
bo-exposure, double exposure, cyberpunk city, robot face

Notice how we use BOTH bo-exposure and double exposure. This combination is crucial - using both terms together gives you the best double exposure effect.
More tutorials are on the way. See you in the next one 👋
GLM-4.6 vs DeepSeek-V3.2: Performance, Benchmarks & DeepInfra Results<p>The open-source LLM ecosystem has evolved rapidly, and two models stand out as leaders in capability, efficiency, and practical usability: GLM-4.6, Zhipu AI’s high-capacity reasoning model with a 200k-token context window, and DeepSeek-V3.2, a sparsely activated Mixture-of-Experts architecture engineered for exceptional performance per dollar. Both models are powerful. Both are versatile. Both are widely adopted […]</p>
Best Open-Source Multimodal AI Models for Production (2026)<p>Open-source multimodal models have a benchmark problem. Every new release comes with DocVQA and MMMU scores, but those numbers rarely reflect how a model performs on a real workload. A model can lead the leaderboard and still struggle with a scanned invoice, a noisy image, or a multi-step agent workflow. Real-world data is far less […]</p>
MiMo-V2.5 Is Now Available on DeepInfra<p>Xiaomi’s MiMo-V2.5 collapses what used to require two separate models — frontier agentic capability and native multimodal understanding — into one. Previously, MiMo-V2-Pro handled agentic and coding tasks while MiMo-V2-Omni covered visual and audio inputs; MiMo-V2.5 replaces both. It handles text, images, video, and audio natively, extends context to 1 million tokens, and scores 71.8 […]</p>
© 2026 DeepInfra. All rights reserved.