Image Generation
Text-to-image models for creating visual content from descriptions
13 models available
Stable Diffusion XL
6.6B9Stability AIThe most advanced open-source image generation model, producing high-quality, photorealistic images from text prompts.
Stable Diffusion 3
8B9.3Stability AILatest generation of Stable Diffusion with improved text rendering, composition, and photorealism.
FLUX.1
12B9.5Black Forest LabsNext-generation image model from the creators of Stable Diffusion, offering unprecedented quality and prompt adherence.
Stable Diffusion 1.5
0.98B7.8Stability AIPopular and widely-used image generation model with extensive community support.
Stable Diffusion 2.1
0.98B7.7Stability AIImproved version with better composition and detail.
Kandinsky 2.2
2.2B8Sber AIRussian-developed image model with unique artistic style.
Playground v2.5
2.5B8.2Playground AIAesthetic-focused model optimized for beautiful, artistic outputs.
PixArt-Σ
0.6B8.3PixArt TeamEfficient high-resolution image generation with fast inference.
Würstchen
1B7.9Würstchen TeamExtremely efficient image model with novel compression approach.
DeepFloyd IF
4.3B8.6Stability AIModular cascaded diffusion model with exceptional text rendering.
Stable Cascade
6.6B8.8Stability AIThree-stage cascaded diffusion model with exceptional quality and efficiency.
SDXL Turbo
2.6B8.3Stability AIDistilled SDXL model for real-time image generation with single-step inference.
LCM LoRA
0.1B (adapter)8.1Latent ConsistencyLatent Consistency Model adapter for fast few-step generation.