image-to-image AI Models

🤖 Model 📝 → 🖼️

cloneofsimo/openjourney_v2_lora

Generates images from text prompts using LoRA (Low-Rank Adaptation) models. Supports loading custom LoRA safetensors fro...

📝 → 🖼️ • text-to-image • image-to-image • image-lora-training • 6.1K runs

🤖 Model 📝 → 🖼️

hunterkamerman/sdxl-clonesy

Generates images in the style of Banksy street art using a fine-tuned SDXL LoRA. Takes text prompts as input and produce...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 63 runs

🤖 Model 🖼️ → 🖼️

cloneofsimo/sdxl-inversion

Performs DDIM inversion on SDXL models to enable precise image editing. Takes an original image with its corresponding p...

🖼️ → 🖼️ • image-editing • image-to-image • 568 runs

🤖 Model 📝 → 🖼️

google/nano-banana-2-lite

Generates images from text prompts, optimized for speed and low cost. Transforms or edits existing images using text des...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 751.3K runs

🤖 Model 📝 → 🖼️

topogoogles/topogoogles_nanobanana

Generates cinematic, character-driven images from text prompts with strong aesthetic control. Fine-tuned for expressive...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 27 runs

🤖 Model 🖼️ → 🖼️

prunaai/p-image-try-on

Generates images of a person wearing specified garments while preserving their face, pose, and body. Takes a person imag...

🖼️ → 🖼️ • virtual-try-on • image-to-image • 108.0K runs

🤖 Model 📝 → 🖼️

bluematter/sdxl-bluejeans

Generates images from text prompts using SDXL fine-tuned specifically on blue jeans imagery. Supports text-to-image gene...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 268 runs

🤖 Model 🖼️ → 🖼️

colinhughes2121/ai-avatar-3d

Converts photos into 3D-rendered character avatars in the style of Roblox, Fortnite, and Discord. Takes a single image a...

🖼️ → 🖼️ • image-to-image • game-asset-generation • 12 runs

🤖 Model 🖼️ → 🖼️

colinhughes2121/cartoon-avatar-maker

Converts photos into clean cartoon-style avatars suitable for profile pictures, gaming avatars, and branded mascots. Use...

🖼️ → 🖼️ • image-to-image • image-style-transfer • 16 runs

🤖 Model 📝 → 🖼️

stspanho/illusion

Creates optical illusion images from text prompts by incorporating depth information. Can generate QR codes with artisti...

📝 → 🖼️ • text-to-image • image-to-image • depth-estimation • 340 runs

🤖 Model 📝 → 🖼️

openai/gpt-image-2

Generates images from text prompts with strong instruction following, sharp text rendering, and detailed photorealism. E...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 26.5M runs