#lora
8 articles
/filters:quality(82)/media/images/1788669894785286893_PwdmwFPZ.webp)
MiniMax H3 Now Makes Images: Text-to-Image and Image Edit APIs Live on WaveSpeedAI
The open-weights MiniMax H3 family now includes two still-image endpoints on WaveSpeedAI: cinematic text-to-image at 1K and 2K from $0.02, and a reference-guided image editor that keeps a person's identity across new scenes, outfits, and styles from $0.03. LoRA variants are available for both.
/filters:quality(82)/media/images/1773962750383987480_n3hqzHRZ.webp)
Master the WaveSpeed Desktop Playground: Batch Processing, LoRA, and Mask Editor
Master WaveSpeed Desktop's Playground features: run batch predictions with auto-randomized seeds, apply LoRA weights, draw masks for inpainting, and manage multiple models in tabs.
How to Train Your Own LoRA Model Without Coding
Learn how to train your own LoRA model on WaveSpeedAI without coding, from preparing a dataset to using the trained model in generation workflows.
Stop Training, Start Creating: Use LoRA on WaveSpeedAI
Learn how to find LoRA models on Hugging Face and Civitai, match them to the correct base model, and use them on WaveSpeedAI.
WaveSpeedAI Desktop Is Here: A Faster, All-in-One AI Creation Experience
WaveSpeedAI Desktop is officially here—bringing speed, focus, and an All-in-One Development and Creation Platform directly to your computer.
/filters:quality(82)/media/images/1744987302874134514_T50XTPLH.webp)
Five New FLUX Models Live on WaveSpeedAI: From Creative Variations to Precision Control
This week, we're introducing five new FLUX model endpoints—each tailored for a specific creative or structural task. Whether you're looking to generate consistent image variations, apply advanced style transfers, or control generation with edge or depth maps, these models expand your creative toolkit with precision and speed.
/filters:quality(82)/media/images/1746804993552508909_hqP9wLW4.webp)
SDXL Now Live on WaveSpeedAI: 2 diffusion-based text-to-image Generative Models
We’re excited to introduce 2 Stable Diffusion XL models now available on WaveSpeedAI: sdxl and sdxl-lora.
/filters:quality(82)/media/images/1745293575288138099_J9TUXY4b.webp)
WAN-2.1 FLF2V Now Live on WaveSpeedAI: From Keyframes to Cinematic Motion
We’re excited to bring another powerful addition to the WAN-2.1 lineup: WAN-2.1 FLF2V (First-Last Frame-to-Video) is now live on WaveSpeedAI. This model introduces a novel approach to video generation by taking a starting frame and a target end frame, and then generating a smooth, dynamic video that transitions between the two. Instead of interpolating or morphing, WAN-FLF2V creates realistic motion informed by text prompts, style, and visual coherence.