image-to-image AI Models

🤖 Model 📝 → 🖼️

black-forest-labs/flux-2-klein-4b

Generates high-quality photorealistic images from text prompts with sub-second inference speed. This 4-billion parameter...

📝 → 🖼️ • text-to-image • image-to-image • image-consistent-character-generation • 21.3M runs

🤖 Model 📝 → 🖼️

wan-video/wan-2.7-image-pro

Generates and edits high-quality images with 4K output support using Alibaba's Wan 2.7 Pro model. Supports text-to-image...

📝 → 🖼️ • text-to-image • image-editing • image-to-image • 152.1K runs

🤖 Model 🖼️ → 🖼️

tengfei-wang/hfgi

Edit facial attributes in images while preserving high-fidelity details like background, appearance, and illumination. U...

🖼️ → 🖼️ • image-editing • image-to-image • 22.2K runs

🤖 Model 🖼️ → 🖼️

lucataco/rivers-stable-diffusion-upscaler

Upscales images using Stable Diffusion with RiversHaveWings' approach, taking an input image and optional text prompt to...

🖼️ → 🖼️ • image-upscaling • image-to-image • 460 runs

🤖 Model 🖼️ → 🖼️

jagilley/stable-diffusion-upscaler

Upscales images using Stable Diffusion's latent diffusion model. Takes an image as input and generates a higher resoluti...

🖼️ → 🖼️ • image-upscaling • image-to-image • 3.6K runs

🤖 Model 📝 → 🖼️

visualizevalue-dev/vv0

Generates images in the style of VV (VisualizeValue) Instagram posts based on text prompts. Trained specifically on Visu...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 152 runs

🤖 Model 📝 → 🖼️

mrharispe/visual-library

Generate images from text prompts using a fine-tuned SDXL model. Supports text-to-image generation, image-to-image trans...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 116 runs

🤖 Model 📝 → 🖼️

mlu108/visualmetaphor

Generates images from text prompts using a LoRA fine-tuned model. Supports text-to-image generation, image-to-image tran...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 125 runs

🤖 Model 🖼️ → 🖼️

yuanrui-mdt-info/sd-1.5-architect-fastest

Generate interior and architectural design images from an input image using a fast and cost-efficient Stable Diffusion 1...

🖼️ → 🖼️ • image-to-image • interior-design • 314 runs

🤖 Model 📝 → 🖼️

fermatresearch/sdxl-weighting-prompts

Generates images from text prompts using SDXL with advanced prompt weighting capabilities through Compel's syntax. Suppo...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 3.5K runs

🤖 Model 📝 → 🖼️

cjwbw/hard-prompts-made-easy

Generates images by automatically discovering optimized prompts from input images using the PEZ algorithm. Takes an inpu...

📝 → 🖼️ • image-to-image • text-to-image • 678 runs