Models tagged "image-to-image"

🤖 Model 📝 → 🖼️

pnickolas1/sdxl-coloringbook

Generate black-and-white coloring book line art from a text prompt. Optionally transform an input image into a coloring-...

📝 → 🖼️ • text-to-image • image-to-image • coloring-book • 38.4K runs

🤖 Model 📝 → 🖼️

scmdr/ai_graphic

Generate stylized graphic illustrations from text prompts. Transform existing images with image-to-image and fill masked...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 312 runs

🤖 Model 🖼️ → 🖼️

tommoore515/pix2pix_tf_albedo2pbrmaps

Generate PBR texture maps from an input texture image. Convert albedo to normal, height (displacement), or smoothness (r...

🖼️ → 🖼️ • image-to-image • game-asset-generation • texture-map-generation • 9.4K runs

🤖 Model 📝 → 🖼️

heavenknowswhat/hvn-2

Generates images in the hvn2 visual style from text prompts. Accepts an optional input image for image-to-image translat...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 108 runs

🤖 Model 📝 → 🖼️

doobls-ai/interor-2

Generate interior design images from text prompts. Transform existing room photos with image-to-image and mask-based inp...

📝 → 🖼️ • interior-design • text-to-image • image-to-image • 23 runs

🤖 Model 📝 → 🖼️

guillaumesimon/radostina2

Generate images from a text prompt, or transform an input image with img2img and mask-based inpainting. Accepts a prompt...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 194 runs

🤖 Model 📝 → 🖼️

fermatresearch/sdxl-controlnet-lora

Generate images from prompts or transform images with SDXL using Canny ControlNet and optional LoRA adapters. Accept a t...

📝 → 🖼️ • text-to-image • image-to-image • controlnet • 962.7K runs

🤖 Model 🖼️

fermatresearch/flux-controlnet-inpaint

Fill masked regions of an image from a text prompt. Accepts an input image, a mask, and an optional ControlNet control i...

🖼️ • image-inpainting • controlnet • lora • 35.9K runs

🤖 Model 📝 → 🖼️

fermatresearch/open-dalle-1.1-lora

Generate images from text prompts, with optional img2img translation and inpainting using a mask. Accept a prompt and op...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 134.1K runs

🤖 Model 📝 → 🖼️

fermatresearch/sdxl-lcm-lora-controlnet

Generate and edit images from text prompts and input images. Leverage SDXL with Latent Consistency Models (LCM) for fast...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 14.9K runs

🤖 Model 🖼️ → 🖼️

black-forest-labs/flux-depth-dev

Edit images with depth guidance from a text prompt and a control image, generating images that preserve the source scene...

🖼️ → 🖼️ • image-to-image • image-editing • depth-guided • 796.9K runs

🤖 Model

cjwbw/midas

Estimate per-pixel depth from a single image and return a dense grayscale relative depth map. Leverage MiDaS with DPT ba...

depth-estimation • 730.6K runs

🤖 Model 📝 → 🖼️

deepfates/flux-bg3

Generate Baldur’s Gate 3–style fantasy portraits and scenes from text prompts. Optionally transform an input image into...

📝 → 🖼️ • text-to-image • image-to-image • baldurs-gate-3 • 400 runs

🤖 Model 📝 → 🖼️

swk23/vader

Generate images of the Star Wars character Darth Vader from text prompts. Optionally use an input image and mask for ima...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 216 runs

🤖 Model 📝 → 🖼️

marcodemutiis/eurotok

Generate images of Eurovision-style singers and stage performances from text prompts. Optionally condition on an input i...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 73 runs

🤖 Model 📝 → 🖼️

citoreh/sima

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

📝 → 🖼️ • text-to-image • lora-person • lora • 4 runs

🤖 Model 📝 → 🖼️

naishagarwal/vaporwave-model

Generate vaporwave-style images from text prompts. Optionally transform an input image (img2img) or inpaint selected reg...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 705 runs

🤖 Model 📝 → 🖼️

aakashapoorv/synthwave

Generate synthwave retro-futurism images from text prompts. Optionally transform an input image or inpaint masked region...

📝 → 🖼️ • text-to-image • image-to-image • synthwave • 31 runs

🤖 Model 📝 → 🖼️

varunv-ux/retropop

Generate retro pop comic-style images from text prompts, with optional image-to-image translation and masked inpainting....

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 48 runs

🤖 Model 📝 → 🖼️

shapestudio/floating-flux

Generate retro-style images from a text prompt or an input image. Perform image-to-image translation and inpainting with...

📝 → 🖼️ • text-to-image • image-to-image • retro-style • 1.7K runs