Models tagged "text-to-image"

🤖 Model 📝 → 🖼️

settai98/sdxl-mm-game-layout

Generate 2D game layout and UI mockups from a text prompt. Output images of screens such as boards, tiles, icons, button...

📝 → 🖼️ • text-to-image • image-inpainting • game-asset-generation • 78 runs

🤖 Model 📝 → 🖼️

mdzor/game-assets

Generate voxel-art game assets from a text prompt. Create blocky, cubic, 3D pixel-art style images suitable for characte...

📝 → 🖼️ • text-to-image • game-asset-generation • voxel-art • 780 runs

🤖 Model 📝 → 🖼️

cybermerlo/cga_pc_game

Generate retro CGA PC game–style, 8-bit pixel-art images from text prompts. Transform an input image or inpaint masked r...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 217 runs

🤖 Model 📝 → 🖼️

veryvanya/flux-ps1-style

Generate PlayStation 1 (PS1) game screenshot–style images from text prompts. Transform existing images to the PS1 aesthe...

📝 → 🖼️ • text-to-image • image-to-image • ps1-style • 3.7K runs

🤖 Model 📝 → 🖼️

jbilcke/sdxl-tombraider

Generate retro, low-poly PS1-era Tomb Raider (1996) style images from text prompts. Optionally transform an input image...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 256 runs

🤖 Model 📝 → 🖼️

andreasjansson/monkey-island-sd

Generate pixel-art images from a text prompt in the style of the classic Monkey Island 1 and 2 point-and-click adventure...

📝 → 🖼️ • text-to-image • pixel-art • monkey-island-style • 2.4K runs

🤖 Model 📝 → 🖼️

cjwbw/gta5_artwork_diffusion

Generate GTA V loading-screen style illustrations from a text prompt. Produce stylized images that mimic GTA5 artwork, t...

📝 → 🖼️ • text-to-image • gta5-style • 4.9K runs

🤖 Model 📝 → 🖼️

fofr/flux-minecraft-movie

Generate Minecraft-style voxel art images from text prompts. Optionally transform an input image or inpaint masked regio...

📝 → 🖼️ • text-to-image • image-to-image • minecraft • 6.7K runs

🤖 Model 📝 → 🖼️

levelsio/san-andreas

Generate GTA: San Andreas, Vice City, and GTA III–style images from text prompts or input images. Transform photos or pe...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 8.4K runs

🤖 Model 📝 → 🖼️

amrdiab568/charify-style

Generate cartoon-style character images from a text prompt. Return a single image in a distinctive vector art look with...

📝 → 🖼️ • text-to-image • character-design • cartoon-style • 156 runs

🤖 Model 📝 → 🖼️

fofr/sdxl-sonic-2-hd

Generate Sonic 2 HD–style 2D platformer game art and screenshots from text prompts. Optionally provide an input image fo...

📝 → 🖼️ • text-to-image • image-to-image • game-asset-generation • 176 runs

🤖 Model 📝 → 🖼️

swetabhsaurav/bolaball-giant

Generate images of the GBOLA game from text prompts, or condition on an input image for image-to-image variations; outpu...

📝 → 🖼️ • text-to-image • image-to-image • gbola • 41 runs

🤖 Model 📝 → 🖼️

dhanushreddy291/forge-saga-landscape

Generate stylized landscape images from a text prompt. Produce fantasy and anime-like environments—mountains, villages,...

📝 → 🖼️ • text-to-image • landscape • 113 runs

🤖 Model 📝 → 🖼️

cjwbw/elden-ring-diffusion

Generate images from text prompts in the Elden Ring game-art style. Use the prompt tokens "elden ring style" to trigger...

📝 → 🖼️ • text-to-image • elden-ring • game-art • 6.9K runs

🤖 Model 📝 → 🖼️

jbilcke/sdxl-zelda64

Generate images in a Nintendo 64 Zelda-inspired style from text prompts. Accept an optional input image for image-to-ima...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 518 runs

🤖 Model 📝 → 🖼️

fofr/sdxl-mario-kart

Generate Mario Kart-style 3D cartoon gameplay images from a text prompt. Optionally transform an input image (img2img) o...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 198 runs

🤖 Model 📝 → 🖼️

madaguru/lauramdg

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

📝 → 🖼️ • text-to-image • lora-person • lora • 353 runs

🤖 Model 📝 → 🖼️

sakshamdembla/sakshamface

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

📝 → 🖼️ • text-to-image • lora-person • lora • 43 runs

🤖 Model 📝 → 🖼️

jiownt/atomaus

Generate images of a character called ATOMAUS from text prompts. Also supports image-to-image and inpainting with a mask...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 74 runs

🤖 Model 📝 → 🖼️

glorbiusthe3rd/amgmerc

Generate images of a Mercedes‑Benz AMG car from text prompts. Optionally transform an input image (img2img) or apply inp...

📝 → 🖼️ • text-to-image • car • mercedes • 82 runs