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

How to use CivitAI LoRAs: 5-Minute AI Guide to Stunning Double Exposure Art
Published on 2025.01.23 by Oguz Vuruskaner
How to use CivitAI LoRAs: 5-Minute AI Guide to Stunning Double Exposure Art

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.

What You'll Need

  • A CivitAI account (free)
  • A DeepInfra account (free)

Set Up a LoRA model

  1. Log in to your DeepInfra account
  2. Navigate to the Deployments section
  3. Click the "New Deployment" button in the top right corner
  4. Select "LoRA text to image" from the options

Once you navigate to this section, you will see a screen like this: Text-to-image LoRA Dashboard 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>
copy

When you have navigated, you should view our classical dashboard, but with your LoRA name.

An Example: Cyberpunk Double Exposure

Now let's create some stunning visuals... Let's break down this stunning example:

bo-exposure, double exposure, cyberpunk city, robot face
copy

Example of AI-generated cyberpunk double exposure art

Key Takeaway ⚠️

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 👋

Related articles
Qwen3.5 397B A17B API Benchmarks: Latency, Throughput & CostQwen3.5 397B A17B API Benchmarks: Latency, Throughput & Cost<p>About Qwen3.5 397B A17B Qwen3.5 397B A17B is Alibaba Cloud&#8217;s largest and most capable multimodal foundation model, released in February 2026. It features a hybrid Mixture-of-Experts (MoE) architecture with 397 billion total parameters and 17 billion active parameters per inference pass, utilizing 512 experts with a routing mechanism selecting a subset per token. This sparse [&hellip;]</p>
Best SaaS Tools and API Providers for MiMo-V2.5Best SaaS Tools and API Providers for MiMo-V2.5<p>As LLM architectures grow increasingly complex, the introduction of the MiMo-V2.5 series represents a significant step forward in multimodal capabilities and massive context handling. Integrating a model with a 1M-token context window and native multimodal support (image, video, audio, text) introduces substantial infrastructure considerations. For developers and enterprise architects, the priorities are clear: managing inference [&hellip;]</p>
DeepSeek Harness Review: Agent Loop & Plugin ArchitectureDeepSeek Harness Review: Agent Loop & Plugin Architecture<p>DeepSeek Harness launched on August 13 and reads like a Claude Code competitor. The framing survives about ten minutes of looking through the source. The repository ships delegation backends named subagent-claude-code and subagent-codex, plus hook bridges that read the hooks.json you already wrote for Claude Code. DeepSeek built a runtime that can hand work to [&hellip;]</p>