image-to-image AI Models

🤖 Model 🖼️ → 🖼️

cjwbw/prompt-free-diffusion

Generate images from visual inputs without text prompts. Accept an input image plus a structural control map (canny edge...

🖼️ → 🖼️ • image-to-image • controlnet • 749 runs

🤖 Model 🖼️ → 🖼️

danjimenezm/food-gen-v1

Generates food images from text prompts and input images. Takes an initial image and transforms it based on the provided...

🖼️ → 🖼️ • image-to-image • food • 337 runs

🤖 Model 📝 → 🖼️

fofr/flux-bad-70s-food

Generate vintage 1970s food photography from a text prompt. Optionally transform an input image or inpaint with a mask t...

📝 → 🖼️ • text-to-image • image-to-image • food • 1.0K runs

🤖 Model 📝 → 🖼️

marcodemutiis/mukbang

Generate mukbang-style food and eating-scene images from a text prompt. Stylize an input image via image-to-image or fil...

📝 → 🖼️ • text-to-image • image-to-image • mukbang • 55 runs

🤖 Model 📝 → 🖼️

ai-image-michael/vedana-chocolate-yogurt-2

Generates images of a specific object or concept called TOK based on text prompts. The trigger word for this LoRA fine-t...

📝 → 🖼️ • text-to-image • lora • 84 runs

🤖 Model 📝 → 🖼️

swetabhsaurav/saladbowl

Generate images of a salad bowl from text prompts. Accepts an input image and optional mask for image-to-image and inpai...

📝 → 🖼️ • text-to-image • image-inpainting • salad-bowl • 77 runs

🤖 Model 📝 → 🖼️

maitrikpatel2025/flux-chips

Generates images of Lay's Classic potato chip bags based on text prompts. The trigger word for this LoRA fine-tune is 'l...

📝 → 🖼️ • text-to-image • lora-object • food • 41 runs

🤖 Model 📝 → 🖼️

gulpdiseno/fajitas

Generate images of a product/packaging called FAJT from text prompts. Optionally transform an input image or fill masked...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 32 runs

🤖 Model 📝 → 🖼️

dave0z/kcafry10004865

Generate images of a Kitchen Couture air fryer from text prompts. Accept optional image and mask inputs for image-to-ima...

📝 → 🖼️ • text-to-image • image-to-image • air-fryer • 65 runs

🤖 Model 📝 → 🖼️

lucataco/flux-dalgona

Generates images of Dalgona cookies based on text prompts. A FLUX fine-tune trained on the distinctive honeycomb toffee...

📝 → 🖼️ • text-to-image • lora • food • 94 runs

🤖 Model 📝 → 🖼️

gneebs/roxys-pizza

Generate retro pizza shop–style graphics from a text prompt. Optionally provide an image for image-to-image stylization...

📝 → 🖼️ • text-to-image • image-to-image • retro-illustration • 33 runs

🤖 Model 📝 → 🖼️

autumnlydon/pistachio-1

Generate images of pistachios from text prompts. Accept an optional input image and mask to perform image-to-image trans...

📝 → 🖼️ • text-to-image • image-to-image • pistachio • 15 runs

🤖 Model 📝 → 🖼️

swetabhsaurav/chopping-board

Generate images of a chopping board called CPBOARD from text prompts. Optionally use an input image and mask for image-t...

📝 → 🖼️ • text-to-image • image-to-image • chopping-board • 32 runs

🤖 Model 📝 → 🖼️

maubad/pizzacalcetin

Generate images of pizza-themed socks (pizzac) from text prompts. Optionally provide an input image and/or mask for imag...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 29 runs

🤖 Model 📝 → 🖼️

nhan4890/artichokeammu

Generate images of the artichokeammu tea product and packaging from text prompts. Accept an optional input image for ima...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 56 runs

🤖 Model 📝 → 🖼️

topogoogles/realbanana

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

📝 → 🖼️ • text-to-image • lora-person • lora • 54 runs

🤖 Model 📝 → 🖼️

olivesforge/sky

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

📝 → 🖼️ • text-to-image • image-to-image • lora-person • 270 runs

🤖 Model 📝 → 🖼️

fofr/sdxl-simpsons-characters

Generate Simpsons-style cartoon characters and portraits from text prompts. Optionally convert an input image to the Sim...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 32.1K runs

🤖 Model 📝 → 🖼️

swk23/ahsoka2

Generate images of a person called TOK from text prompts, with optional image-to-image and image inpainting. The trigger...

📝 → 🖼️ • text-to-image • image-to-image • lora-person • 96 runs

🤖 Model 📝 → 🖼️

arietudo/samm

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

📝 → 🖼️ • text-to-image • lora-person • lora • 832 runs