image-to-image AI Models

🤖 Model 📝 → 🖼️

cjwbw/supermarionation

Generate Supermarionation-style puppet images from text prompts or by stylizing an input image. Produce Thunderbirds/Ger...

📝 → 🖼️ • text-to-image • image-to-image • 1.9K runs

🤖 Model 📝 → 🖼️

crivera/sketch-lora

Generate pencil sketch images from a text prompt or convert an input image into a hand-drawn sketch. Accept an optional...

📝 → 🖼️ • text-to-image • image-to-image • pencil-sketch • 10.9K runs

🤖 Model 🖼️ → 🖼️

jagilley/controlnet-pose

Generate pose-guided images from an input image of a person and a text prompt. Extracts a human pose map with OpenPose a...

🖼️ → 🖼️ • image-to-image • controlnet • openpose • 175.4K runs

🤖 Model 📝 → 🖼️

swartype/sdxl-pixar

Generate Pixar-style, 3D animated illustrations and posters from a text prompt. Optionally transform an input image into...

📝 → 🖼️ • text-to-image • image-to-image • pixar-style • 656.3K runs

🤖 Model 🖼️ → 🖼️

412392713/vtoonify

Stylize portrait photos into cartoon, comic, Arcane, Pixar, caricature, or illustration looks. Takes a single face image...

🖼️ → 🖼️ • image-style-transfer • image-to-image • cartoonization • 113.2K runs

🤖 Model 🖼️ → 🖼️

viktorfa/oot_diffusion

Generate virtual try-on images of a person wearing an upper-body garment. Input a clear photo of the model and a product...

🖼️ → 🖼️ • virtual-try-on • image-to-image • 23.0K runs

🤖 Model 🖼️

juergengunz/ultimate-portrait-upscale

Upscale portrait images using ControlNet Tile technology. Takes a portrait image and increases its resolution by a speci...

🖼️ • image-upscaling • 50.4K runs

🤖 Model 🖼️ → 🖼️

lucataco/demofusion-enhance

Enhances input images by generating higher-resolution versions using DemoFusion, a technique that enables higher-resolut...

🖼️ → 🖼️ • image-to-image • image-upscaling • 11.2K runs

🤖 Model 🖼️ → 🖼️

fermatresearch/high-resolution-controlnet-tile

Upscales images to higher resolutions using ControlNet 1.1 tile technology while preserving and enhancing original detai...

🖼️ → 🖼️ • image-upscaling • image-to-image • 656.4K runs

🤖 Model 🖼️

fewjative/ultimate-sd-upscale

Upscales images using Ultimate SD Upscale with ControlNet Tile integration. Takes an input image and generates a higher...

🖼️ • image-upscaling • 166.8K runs

🤖 Model 🖼️ → 🖼️

fermatresearch/magic-image-refiner

Refines and enhances input images using ControlNet technology to improve quality and detail while preserving the origina...

🖼️ → 🖼️ • image-editing • image-upscaling • image-inpainting • 952.8K runs

🤖 Model 🖼️ → 🖼️

lucataco/controlnet-tile

Upscales and enhances images using ControlNet v1.1 Tile conditioning. Takes an input image and applies diffusion-based p...

🖼️ → 🖼️ • image-upscaling • image-to-image • 4.3K runs

🤖 Model 📝 → 🖼️

ranthonyb/fluxconcert2

Generate concert and live music scene images from text prompts. Optionally transform an input image or inpaint regions w...

📝 → 🖼️ • text-to-image • image-to-image • concert • 35 runs

🤖 Model 📝 → 🖼️

zeg06/sisco

Generates images of a person called sisco based on text prompts. The trigger word for this LoRA fine-tune is 'sisco'.

📝 → 🖼️ • text-to-image • image-to-image • lora-person • 160 runs

🤖 Model 📝 → 🖼️

gawasa29/testna

Generate movie-poster style images from text prompts. Transform an input image or inpaint with a mask to adapt or extend...

📝 → 🖼️ • text-to-image • image-to-image • movie-poster • 20 runs

🤖 Model 📝 → 🖼️

oliverobenrauch/ai-ldgrstx

Generate images of the Ledger Stax crypto hardware wallet from text prompts. Optionally transform or inpaint the device...

📝 → 🖼️ • text-to-image • image-inpainting • ledger-stax • 10 runs

🤖 Model 📝 → 🖼️

cbh123/sdxl-money

Generate banknote and currency-style images from text prompts. Optionally transform an input image into a money aestheti...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 5.6K runs

🤖 Model 📝 → 🖼️

amrita-sportpit/zrtkv

Generates images of a person called ZTKV based on text prompts. The trigger word for this LoRA fine-tune is 'ZTKV'.

📝 → 🖼️ • text-to-image • lora-person • lora • 76 runs

🤖 Model 📝 → 🖼️

richards630620/cyalon

Generates images of a person called Cyalon based on text prompts. The trigger word for this LoRA fine-tune is 'Cyalon'.

📝 → 🖼️ • text-to-image • lora-person • lora • 77 runs

🤖 Model 📝 → 🖼️

mike-freeai/hx8y

Generate images from text prompts, or edit existing images via image-to-image and masked inpainting. Accept a prompt plu...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 26 runs