image-to-image AI Models

🤖 Model 📝 → 🖼️

cjwbw/stable-diffusion-v2

Generate images from text prompts or create prompt-guided variations of an input image. Outputs images at 768×768 by def...

📝 → 🖼️ • text-to-image • image-to-image • 280.5K runs

🤖 Model 🖼️ → 🖼️

lambdal/stable-diffusion-image-variation

Generate image variations from an input image. Use a Stable Diffusion model fine-tuned to accept CLIP image embeddings (...

🖼️ → 🖼️ • image-to-image • image-variation • 370.0K runs

🤖 Model 📝 → 🖼️

tommoore515/material_stable_diffusion

Generate seamless, tileable images and textures from a text prompt. Produce repeating materials, patterns, and backgroun...

📝 → 🖼️ • text-to-image • image-to-image • tileable-textures • 390.0K runs

🤖 Model 🖼️ → 🖼️

zust-ai/zust-diffusion

Compose product photos into new scenes from a text prompt. Input a background scene image and one or more subject/produc...

🖼️ → 🖼️ • image-to-image • image-editing • product-photography • 61.8K runs

🤖 Model 🖼️ → 🖼️

oliland/cog-diffusionlight-turbo

Transforms images by adding reflective chrome sphere elements with realistic lighting and shadow effects. Takes an input...

🖼️ → 🖼️ • image-to-image • image-editing • 83 runs

🤖 Model 🖼️ → 🖼️

jagilley/stable-diffusion-depth2img

Create variations of an input image guided by a text prompt while preserving scene structure via depth-to-image conditio...

🖼️ → 🖼️ • image-to-image • image-editing • 59.6K runs

🤖 Model 📝 → 🖼️

cjwbw/stable-diffusion

Generate images from text, or transform an input image and inpaint masked regions. Supports negative prompts and additio...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 65.4K runs

🤖 Model 📝 → 🖼️

nightmareai/disco-diffusion

Generate stylized images from text prompts. Optionally start from an init image or guide toward a target image to blend...

📝 → 🖼️ • text-to-image • image-to-image • 64.7K runs

🤖 Model 📝 → 🖼️

afiaka87/clip-guided-diffusion

Generate images from a text prompt using CLIP-guided diffusion. Optionally provide an init image to blend with the diffu...

📝 → 🖼️ • text-to-image • image-to-image • 43.1K runs

🤖 Model 📝 → 🖼️

lucataco/stable-diffusion-3.5-large-lora

Generate images from text prompts or transform input images (img2img) with Stable Diffusion 3.5 Large while applying ext...

📝 → 🖼️ • text-to-image • image-to-image • 2.2K runs

🤖 Model 📝 → 🖼️

realkingsofasia/musashi

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

📝 → 🖼️ • text-to-image • lora-person • lora • 482 runs

🤖 Model 🖼️ → 🖼️

fofr/face-to-many

Transform a person’s photo into stylized avatars in 3D, Emoji, Video game, Pixels, Clay, or Toy styles. Accepts a single...

🖼️ → 🖼️ • image-to-image • image-consistent-character-generation • avatar-generation • 14.7M runs

🤖 Model 🖼️ → 🖼️

tencentarc/photomaker

Generate images of a specific person in new styles and scenarios from one or more input photos. Provide 1–4 human refere...

🖼️ → 🖼️ • image-to-image • image-consistent-character-generation • 8.3M runs

🤖 Model 🖼️ → 🖼️

pikachupichu25/live-portrait-image

Transfers facial expressions from a driving image to a source image using LivePortrait technology. Takes two input image...

🖼️ → 🖼️ • image-to-image • face-swap • 165.6K runs

🤖 Model 🖼️ → 🖼️

timothybrooks/instruct-pix2pix

Edit images from natural-language instructions. Takes an input image and a text prompt describing the edit and outputs o...

🖼️ → 🖼️ • image-editing • image-to-image • 920.0K runs

🤖 Model 🖼️ → 🖼️

grandlineai/instant-id-photorealistic

Generate photorealistic images of a person from a single reference photo and a text prompt, preserving identity across n...

🖼️ → 🖼️ • image-consistent-character-generation • image-to-image • 43.7K runs

🤖 Model 📝 → 🖼️

ostris/flux-dev-lora-trainer

Train LoRA adapters for FLUX.1 (dev and schnell) from an image dataset, then generate images from text or edit existing...

📝 → 🖼️ • image-lora-training • text-to-image • image-to-image • 799.3K runs

🤖 Model 📝 → 🖼️

richard-megavision/model_laylite

Generate images of a coarsely corrugated HDPE culvert pipe called model_laylite from text prompts. Optionally provide an...

📝 → 🖼️ • text-to-image • image-to-image • culvert-pipe • 29 runs

🤖 Model 📝 → 🖼️

shashankanil/sdxl-test

Generate images of Indian road scenes from text prompts, with optional image-to-image translation and inpainting. Use fo...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 89 runs

🤖 Model 🖼️ → 🖼️

tencentarc/photomaker-style

Generate stylized portraits and avatars from one or more input photos of a person. Provide a text prompt that includes t...

🖼️ → 🖼️ • image-to-image • image-consistent-character-generation • 1.5M runs