text-to-image AI Models

🤖 Model 📝 → 🖼️

abarzuamedios/adle_chris

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

📝 → 🖼️ • text-to-image • lora-person • lora • 1.2K runs

🤖 Model 📝 → 🖼️

nvidia/sana

Generates high-resolution images up to 4096x4096 from text prompts with fast generation speed. Uses linear diffusion tra...

📝 → 🖼️ • text-to-image • 257.4K runs

🤖 Model 📝 → 🖼️

prunaai/sdxl-lightning

Generate images from text prompts with SDXL-Lightning for low-latency, few-step diffusion optimized for A100 inference....

📝 → 🖼️ • text-to-image • sdxl • fast-inference • 669 runs

🤖 Model 📝 → 🖼️

fofr/sticker-maker

Generates sticker-style graphics with transparent backgrounds from text prompts. Creates cartoon-style illustrations wit...

📝 → 🖼️ • text-to-image • background-removal • 2.5M runs

🤖 Model 📝 → 🖼️

maitreyarish/visnu

Generate images of the Hindu deity Vishnu from text prompts. The trigger word for this LoRA fine-tune is 'vishnu'.

📝 → 🖼️ • text-to-image • lora-person • lora-famous-person • 174 runs

🤖 Model 📝 → 🖼️

mcgregory99/goyofacebooth

Generate images of the 'gycn' subject from a text prompt or a reference image. Use the trigger keyword 'gycn' to activat...

📝 → 🖼️ • text-to-image • image-to-image • 75 runs

🤖 Model 📝 → 🖼️

andreasjansson/monkey-island-rdm

Generate Monkey Island–style pixel-art game scenes from a text prompt. Accepts a text prompt (automatically prefixed wit...

📝 → 🖼️ • text-to-image • pixel-art • 623 runs

🤖 Model 📝 → 🖼️

pwntus/sdxl-gta-v

Generate GTA V–style images from a text prompt. Optionally transform an input image (image-to-image) and inpaint masked...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 64.6K runs

🤖 Model 📝 → 🖼️

replicate/flux-2d-game-assets

Generate 2D game assets from a text prompt or an input image. Use image-to-image and masked inpainting to iterate on ico...

📝 → 🖼️ • game-asset-generation • text-to-image • image-inpainting • 522 runs

🤖 Model 📝 → 🖼️

dribnet/pixray-genesis

Generate images from a text prompt. Accept a short title prompt plus optional settings text, and return one or more imag...

📝 → 🖼️ • text-to-image • 160.7K runs

🤖 Model 📝 → 🖼️

steliosm/backgrounds_v1

Generate cartoon-style game backgrounds from text prompts. Optionally transform an input image or inpaint regions with a...

📝 → 🖼️ • text-to-image • image-inpainting • game-asset-generation • 126 runs

🤖 Model 📝 → 🖼️

cloneofsimo/gta5_lora

Generate images using custom LoRA models loaded from provided URLs. Supports text-to-image generation with LoRA concept...

📝 → 🖼️ • text-to-image • image-to-image • image-lora-training • 12.1K runs

🤖 Model 📝 → 🖼️

lucataco/flux-game-assets

Generate 2D game assets from text prompts. Convert existing images (image-to-image) or fill masked regions (inpainting)...

📝 → 🖼️ • text-to-image • image-to-image • game-asset-generation • 278 runs

🤖 Model 📝 → 🖼️

galleri5/icons

Generate flat, pop-constructivist icons and graphic illustrations from text prompts. Output stylized, minimalist images...

📝 → 🖼️ • text-to-image • image-to-image • icon-generation • 29.3K runs

🤖 Model 📝 → 🖼️

andyx1976/dress_shirt

Generates images of plain men's dress shirts based on text prompts. Produces slim fit dress shirts in white, blue, and c...

📝 → 🖼️ • text-to-image • lora • clothing • 49 runs

🤖 Model 📝 → 🖼️

andyx1976/checkshirt1

Generate images of people wearing checkered (checked/plaid) dress shirts from text prompts. Optionally take an input ima...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 223 runs

🤖 Model 📝 → 🖼️

deepfates/deepfits_flux_dev

Generate fashion-focused images of clothing, outfits, and editorial looks from a text prompt. Optionally provide an inpu...

📝 → 🖼️ • text-to-image • image-to-image • fashion • 18.7K runs

🤖 Model 📝 → 🖼️

stoodioai/clovia-blue-nightwear

Generates images of Clovia blue nightwear based on textual prompts. The trigger word for this LoRA fine-tune is 'clovia-...

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

🤖 Model 📝 → 🖼️

diazdiaz/uggator

Generate images of slipper-style footwear from text prompts. Optionally take an input image for image-to-image translati...

📝 → 🖼️ • text-to-image • image-to-image • slipper • 68 runs

🤖 Model 📝 → 🖼️

omniedgeio/deepfashionsdxl

Generate fashion and clothing images using a specialized SDXL model trained on fashion data. Supports text-to-image gene...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 1.3K runs