image-to-image AI Models

🤖 Model 🖼️ → 🖼️

bytedance/flux-pulid

Generate identity-consistent images of a person from a reference face image and a text prompt. Preserve facial identity...

🖼️ → 🖼️ • image-consistent-character-generation • image-to-image • 2.4M runs

🤖 Model 📝 → 🖼️

fofr/flux-klingon

Generate images of Klingons from the Star Trek universe based on text prompts. Optionally transform an input image or in...

📝 → 🖼️ • text-to-image • image-to-image • klingon • 213 runs

🤖 Model 🖼️ → 🖼️

espressotechie/qwen-imgedit-4bit

Edit images using text instructions. Accepts an input image and a text prompt (optionally a negative prompt) and returns...

🖼️ → 🖼️ • image-editing • image-to-image • 524 runs

🤖 Model 🖼️ → 🖼️

zylim0702/qwen-multi-view-advanced

Generates multiple view angles of a character or object from a single input image. Takes an image and creates front, sid...

🖼️ → 🖼️ • image-to-image • image-consistent-character-generation • 463 runs

🤖 Model 📝 → 🖼️

colinmcdonnell22/ghiblify-3

Generate Studio Ghibli–style images from text prompts or transform input images into Ghibli-style artwork. Accept an opt...

📝 → 🖼️ • text-to-image • image-to-image • ghibli-style • 430.2K runs

🤖 Model 📝 → 🖼️

bnhomebr/sil

Generates images of a person called SSERAF from text prompts, with optional image-to-image and masked inpainting inputs;...

📝 → 🖼️ • text-to-image • image-to-image • lora-person • 80 runs

🤖 Model 📝 → 🖼️

swk23/leia

Generate images of the character Leia Organa from text prompts or an input image, with optional inpainting. The trigger...

📝 → 🖼️ • text-to-image • lora-person • lora-famous-person • 90 runs

🤖 Model 📝 → 🖼️

swk23/maul-live

Generates images of the Star Wars character Darth Maul based on text prompts. The trigger word for this LoRA fine-tune i...

📝 → 🖼️ • text-to-image • lora-person • lora-famous-person • 22 runs

🤖 Model 📝 → 🖼️

topogoogles/nanotopo

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

📝 → 🖼️ • text-to-image • lora • lora-person • 17 runs

🤖 Model 📝 → 🖼️

nhan4890/solanumprocumbensteabox

Generates images of a specific object called Solanumprocumbensteabox based on text prompts. The trigger word for this Lo...

📝 → 🖼️ • text-to-image • lora • 10 runs

🤖 Model 📝 → 🖼️

littlereza/therain

Generate rainy, cinematic urban images from a text prompt. Emphasizes rain-soaked scenes, wet pavement reflections, mood...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 20 runs

🤖 Model 📝 → 🖼️

mumu831/hachee1.0

Generate images of a dog called Hachee from text prompts. The trigger word for this LoRA fine-tune is 'Hachee'.

📝 → 🖼️ • text-to-image • dog • lora • 16 runs

🤖 Model 📝 → 🖼️

kuralay-ai/kuralai

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

📝 → 🖼️ • text-to-image • lora-person • lora • 61 runs

🤖 Model 📝 → 🖼️

darklion84/lerabuns

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

📝 → 🖼️ • text-to-image • lora-person • lora • 80 runs

🤖 Model 📝 → 🖼️

ccchot-osk103/pai_daughter

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

📝 → 🖼️ • text-to-image • lora-person • lora • 47 runs

🤖 Model 🖼️

google-research/maxim

Restore and enhance photos from an input image, returning a cleaned image. Choose task-specific presets for denoising, d...

🖼️ • image-restoration • image-enhancement • 547.1K runs

🤖 Model 🖼️ → 🖼️

tomclive/sceneideas

Generate multiple cinematic scene ideas from a single reference image. Take one image as input and output a batch of abo...

🖼️ → 🖼️ • image-to-image • storyboard-generation • 61 runs

🤖 Model 📝 → 🖼️

swetabhsaurav/4-in-a-row

Generate images of a 4-in-a-row board game called BOLACON from text prompts. Optionally provide an image (and mask) for...

📝 → 🖼️ • text-to-image • image-to-image • board-game • 56 runs

🤖 Model 📝 → 🖼️

aliadhami/3d-sheet

Generates technical 3D reference sheets showing objects from three consistent views (front, back, and side) with minimal...

📝 → 🖼️ • text-to-image • lora • technical-reference • 328 runs

🤖 Model 📝 → 🖼️

roblo3x/lora-3d-avatars

Generates 3D avatar-style images based on text prompts. The trigger word for this LoRA fine-tune is 'AVATAR'. The trigge...

📝 → 🖼️ • text-to-image • lora • avatar • 317 runs