image-to-image AI Models

🤖 Model 📝 → 🖼️

settyan/flash-beta.3

Generate images from text prompts, with optional image-to-image translation and masked inpainting edits. Switch between...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 93 runs

🤖 Model 🖼️ → 🖼️

jd7h/zero123plusplus

Generate consistent multi-view images from a single input image. Provide a square image (>=320x320), and it synthesizes...

🖼️ → 🖼️ • image-to-image • novel-view-synthesis • 11.0K runs

🤖 Model 📝 → 🖼️

leonardoa2/masc

Generate cinematic, flash-lit documentary-style images from a text prompt. Accepts an optional input image for image-to-...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 438 runs

🤖 Model 📝 → 🖼️

leonardoa2/cult-contemplazione

Generate grainy 35mm flash-photography–style images from text prompts, with optional image-to-image translation and inpa...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 361 runs

🤖 Model 📝 → 🖼️

markredito/90sbadtrip

Generate images in a retro, trippy 1990s bad-CGI aesthetic from text prompts. Optionally condition on an input image for...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 2.3K runs

🤖 Model 📝 → 🖼️

creativeathive/lemaar-doorhandle-newset

Generate images of a door handle called lemndoorhandle from text prompts. Optionally take an input image and a mask to p...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 42 runs

🤖 Model 🖼️ → 🖼️

adirik/t2i-adapter-sdxl-canny

Edit images from a text prompt while preserving structure using canny edge guidance (T2I-Adapter for SDXL). Provide an i...

🖼️ → 🖼️ • image-to-image • image-editing • 138.3K runs

🤖 Model 🖼️ → 🖼️

adirik/t2i-adapter-sdxl-depth-midas

Edit images from an input image and text prompt using SDXL T2I-Adapter with MiDaS depth guidance. Preserve scene geometr...

🖼️ → 🖼️ • image-to-image • image-editing • depth-guided • 653.6K runs

🤖 Model 📝 → 🖼️

vectorspacelab/omnigen

Generate images from text prompts or multimodal prompts that combine text with up to three reference images, and perform...

📝 → 🖼️ • text-to-image • image-to-image • image-editing • 12.6K runs

🤖 Model 🖼️ → 🖼️

mcai/dreamshaper-v6-img2img

Generate variations of an input image guided by a text prompt. Transform photos or art by controlling change strength, s...

🖼️ → 🖼️ • image-to-image • image-editing • 169.0K runs

🤖 Model 🖼️ → 🖼️

cjwbw/diffae

Edit face attributes in an input image. Provide a face photo and select a target attribute (e.g., Bangs, Blond_Hair, Bla...

🖼️ → 🖼️ • image-editing • image-to-image • face-editing • 17.1K runs

🤖 Model 🖼️ → 🖼️

meepo-pro-player/invoker

Transform an input image according to a text prompt while preserving spatial structure with ControlNet. Accepts an image...

🖼️ → 🖼️ • image-to-image • image-editing • controlnet • 34.9K runs

🤖 Model 🖼️ → 🖼️

philz1337x/controlnet-deliberate

Edit images from a text prompt while preserving structure using ControlNet Canny guidance. Takes an input image and a pr...

🖼️ → 🖼️ • image-to-image • image-editing • controlnet • 1.1M runs

🤖 Model 🖼️ → 🖼️

tmcdepix/zone

Edit specific regions of an image using natural-language instructions, returning an edited image. Leverage ZONE (Zero-Sh...

🖼️ → 🖼️ • image-editing • image-to-image • 177 runs

🤖 Model 🖼️ → 🖼️

cjwbw/diffedit-stable-diffusion

Edit images using text prompts with automatic, semantic mask guidance. Provide an input image and a source prompt to det...

🖼️ → 🖼️ • image-editing • image-to-image • 415 runs

🤖 Model 📝 → 🖼️

afiaka87/ldm-autoedit

Generate images from text prompts or apply text‑guided edits to an input image. Control coarse‑to‑fine changes over time...

📝 → 🖼️ • text-to-image • image-editing • 1.5K runs

🤖 Model 🖼️ → 🖼️

lucataco/flux-rf-inversion

Edit an input image with a text prompt to generate a modified image while preserving structure and composition. Leverage...

🖼️ → 🖼️ • image-editing • image-to-image • 213 runs

🤖 Model 📝 → 🖼️

adirik/prompt-to-prompt-realvisxl-3.0

Edit images using text prompts with the Prompt-to-Prompt technique on RealVisXL V3.0, a model trained to generate photor...

📝 → 🖼️ • image-editing • text-to-image • 465 runs

🤖 Model 📝 → 🖼️

adirik/sdxl-prompt-to-prompt

Edit images using Prompt-to-Prompt techniques for SDXL architecture by modifying text prompts to generate variations of...

📝 → 🖼️ • image-editing • text-to-image • 264 runs

🤖 Model 📝 → 🖼️

adcopy-ai/reversedhat

Generate images of a hat with mirrored front lettering from text prompts. Optionally use an input image and mask to inse...

📝 → 🖼️ • text-to-image • image-inpainting • hat • 201 runs