Image Models
Image AI models on LORY
27 images available — explore each model's strengths, then try it in your own story project.
Flux 1.1 Pro
High-fidelity text-to-image model with strong composition and lighting consistency.
Flux 2 Pro – Composite
Reference-aware image compositing model for combining subjects into coherent final scenes.
Flux 2 Pro – Edit
Precision image editing model for guided transformations while keeping source identity.
Imagen 4 Standard – Generate
Balanced Imagen 4 profile for strong detail quality with practical turnaround speed.
Nano Banana (Flash) – Composite
Gemini Flash composite profile for low-latency merges and early visual exploration.
Nano Banana (Flash) – Edit
Gemini Flash edit profile tuned for quick fixes, variants, and lightweight changes.
Nano Banana (Flash) – Generate
Gemini Flash generate profile for fast, low-cost image drafts.
Nano Banana 2 (Flash) – Composite
Gemini 3.1 Flash Image composite profile for fast, high-throughput reference merges.
Nano Banana 2 (Flash) – Edit
Gemini 3.1 Flash Image edit profile for rapid iterations with stronger image quality.
Nano Banana 2 (Flash) – Generate
Gemini 3.1 Flash Image generate profile balancing speed and quality for concept production.
Nano Banana Pro – Composite
Gemini Pro composite profile with better detail retention and scene cohesion.
Nano Banana Pro – Edit
Gemini Pro edit profile for higher-fidelity revisions and cleaner output quality.
Nano Banana Pro – Generate
Gemini Pro generate profile for richer detail and stronger final-image polish.
OpenAI gpt-image-2 – Composite
gpt-image-2 composite profile that blends up to 10 high-fidelity references into a single cohesive scene.
OpenAI gpt-image-2 – Edit
gpt-image-2 edit profile with automatic high-fidelity input processing for detailed, identity-aware edits.
OpenAI gpt-image-2 – Generate
Latest OpenAI text-to-image model with stronger prompt adherence, improved text rendering, and flexible sizes.
OpenAI gpt-image-2 – Inpaint
gpt-image-2 mask-based inpainting for surgical replacements with strong scene and lighting continuity.
OpenAI Image 1.5 – Composite
OpenAI composite variant for prompt-following scene assembly from reference assets.
OpenAI Image 1.5 – Edit
OpenAI image editing model for controlled transformations with stable structure.
OpenAI Image 1.5 – Generate
Balanced text-to-image model for clean results across broad creative prompts.
OpenAI Image 1.5 – Inpaint
Inpainting-focused model for mask-based replacements that preserve scene continuity.
Qwen Image Edit LoRA
LoRA-capable edit model that is strong at stylized changes and localized revisions.
Qwen Image LoRA – Composite
LoRA-powered compositing variant for consistent style transfer across mixed references.
Seedream 5 Lite – Composite
Bytedance Seedream 5 Lite multi-reference composition — accepts up to 10 reference images and blends them via prompt-led restyling, with Figure 1 /…
Seedream 5 Lite – Edit
Bytedance Seedream 5 Lite single-image edit profile — prompt-led transformation with preserved composition and framing. Best for end-state edits ("change…
Z-Image Turbo – Composite
Speed-oriented compositing model for quick prompt-plus-reference blends.
Z-Image Turbo – Edit
Fast image edit model ideal for rapid concept iterations and prompt tweaks.