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-4.7-Flash API Benchmarks: Latency, Throughput & Cost<p>About GLM-4.7-Flash GLM-4.7-Flash is Z.AI’s open-weights reasoning model released in January 2026. Built on a Mixture-of-Experts (MoE) Transformer architecture, it features 30 billion total parameters with only ~3 billion active per inference — making it exceptionally efficient for its capability class. The model is designed as a lightweight, cost-effective alternative to Z.AI’s flagship GLM-4.7, optimized […]</p>
GLM-4.6 API: Get fast first tokens at the best $/M from Deepinfra's API - Deep Infra<p>GLM-4.6 is a high-capacity, “reasoning”-tuned model that shows up in coding copilots, long-context RAG, and multi-tool agent loops. With this class of workload, provider infrastructure determines perceived speed (first-token time), tail stability, and your unit economics. Using ArtificialAnalysis (AA) provider charts for GLM-4.6 (Reasoning), DeepInfra (FP8) pairs a sub-second Time-to-First-Token (TTFT) (0.51 s) with the […]</p>
Qwen3 Coder 480B A35B API Benchmarks: Latency & Cost<p>About Qwen3 Coder 480B A35B Instruct Qwen3 Coder 480B A35B Instruct is a state-of-the-art large language model developed by the Qwen team at Alibaba Cloud, specifically designed for code generation and agentic coding tasks. It is a Mixture-of-Experts (MoE) model with 480 billion total parameters and 35 billion active parameters per inference, enabling high performance […]</p>
© 2026 DeepInfra. All rights reserved.