text-to-image AI Models

🤖 Model 📝 → 🖼️

aleksa-codes/flux-ghibsky-illustration

Generates images with a unique artistic style that blends Ghibli-inspired whimsical elements with Makoto Shinkai's atmos...

📝 → 🖼️ • text-to-image • lora-style • anime • 167.0K runs

🤖 Model 📝 → 🖼️

fofr/sdxl-barbie

Generate Barbie movie–style images from a text prompt. Optionally transform an input image into this pastel, glossy, dol...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 40.8K runs

🤖 Model 📝 → 🖼️

karanchawla/studio-ghibli

Generate Studio Ghibli–style illustrations from text prompts. Optionally translate an input image into this aesthetic or...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 35.7K runs

🤖 Model 📝 → 🖼️

tstramer/classic-anim-diffusion

Generate classic animation–style cartoon illustrations from a text prompt. Produce Disney-like 2D character art and scen...

📝 → 🖼️ • text-to-image • cartoon-style • disney-style • 52.9K runs

🤖 Model 📝 → 🖼️

paappraiser/retro-coloring-book

Generate retro 1960s coloring-book line art from a text prompt. Transform an input image into black-and-white outlines o...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 17.6K runs

🤖 Model 📝 → 🖼️

doriandarko/sdxl-hiroshinagai

Generate illustrations in the style of Hiroshi Nagai from text prompts. Optionally translate an input image into this fi...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 31.8K runs

🤖 Model 📝 → 🖼️

tstramer/archer-diffusion

Generate Archer-style cartoon images from a text prompt. Produce cel-shaded portraits, characters, objects, and scenes w...

📝 → 🖼️ • text-to-image • archer-style • cartoon • 34.8K runs

🤖 Model 📝 → 🖼️

tstramer/sd-pokemon-diffusion

Generate Pokémon-style images from a text prompt. Produce creature and character illustrations in the Pokémon aesthetic...

📝 → 🖼️ • text-to-image • pokemon • 19.5K runs

🤖 Model 📝 → 🖼️

fofr/make-someone

Generate images and videos of people based on textual prompts describing their appearance. Create multiple variations of...

📝 → 🖼️ • image-generation • video-generation • text-to-image • 2 runs

🤖 Model 📝 → 🖼️

pipeline-examples/prompter

Generate images from text prompts by creating and refining prompt templates based on a given theme. Utilize a language m...

📝 → 🖼️ • text-to-image • prompt-generation • image-generation • 16 runs

🤖 Model 📝 → 🖼️

parkjaewoo-1/cat_rudy_v2

Generate images of a specific cat called CATRUDY from text prompts, with optional image-to-image and inpainting to inser...

📝 → 🖼️ • text-to-image • image-to-image • cat • 59 runs

🤖 Model 📝 → 🖼️

el8245/sico

Generate images of a vehicle called SICOCAR from text prompts. Optionally transform an input image or fill masked region...

📝 → 🖼️ • text-to-image • image-to-image • car • 204 runs

🤖 Model 📝 → 🖼️

senatoracadia/pulp

Generate mid-20th-century pulp magazine and paperback cover art from text prompts. Optionally transform an input image i...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 241 runs

🤖 Model 📝 → 🖼️

jyoung105/stable-cascade

Generate images from a text prompt. Uses Stability AI’s Stable Cascade (Würstchen) diffusion architecture with separate...

📝 → 🖼️ • text-to-image • 79 runs

🤖 Model 📝 → 🖼️

lukevink/ericadress_sf2.1_pxw

Generate fashion-focused images from a text prompt. Produce photorealistic, studio-style apparel shots of models (e.g.,...

📝 → 🖼️ • text-to-image • fashion • 4.3K runs

🤖 Model 📝 → 🖼️

olucasfigueiredo/kadusantos

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

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

🤖 Model 📝 → 🖼️

abyssalsoul/cyberdad

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

📝 → 🖼️ • text-to-image • lora-person • lora • 116 runs

🤖 Model 📝 → 🖼️

moicarmonas/nofunciono-c

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

📝 → 🖼️ • lora-person • text-to-image • image-to-image • 79 runs

🤖 Model 📝 → 🖼️

danielgiet/c

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 • 22 runs

🤖 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