Models tagged "text-to-image"

🤖 Model 📝 → 🖼️

torrikabe-ai/nipismadu

Generate images of the Nipis Madu soda bottle from text prompts. Optionally supply an input image and/or a mask for imag...

📝 → 🖼️ • text-to-image • image-to-image • nipis-madu • 106 runs

🤖 Model 📝 → 🖼️

jerakst/banochka

Generate images of a specific jar/bottle product called BANOCHKAMAS from a text prompt. Optionally provide an input imag...

📝 → 🖼️ • text-to-image • image-to-image • jar • 49 runs

🤖 Model 📝 → 🖼️

krisdoan/au2115n

Generate images of the AU2115N eyeglass frame from text prompts. Optionally edit an input image or masked region to inpa...

📝 → 🖼️ • text-to-image • image-inpainting • eyeglasses • 52 runs

🤖 Model 📝 → 🖼️

google/gemini-2.5-flash-image

Generate and edit images from a text prompt with optional one or more reference images. Combine multiple input images in...

📝 → 🖼️ • text-to-image • image-editing • image-to-image • 743.7K runs

🤖 Model 📝 → 🖼️

aramintak/gemini-anime

Generate anime-style images from a text prompt. Use the trigger phrase "daiton style" to activate the LoRA aesthetics an...

📝 → 🖼️ • text-to-image • anime • 79 runs

🤖 Model 📝 → 🖼️

adirik/flux-cinestill

Generate CineStill-style film images from a text prompt. Optionally transform an input image or inpaint masked regions t...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 116.3K runs

🤖 Model 📝 → 🖼️

cjwbw/analog-diffusion

Generate images from text prompts with an analog film photography look. Use the activation token "analog style" to evoke...

📝 → 🖼️ • text-to-image • analog-film • nsfw • 234.6K runs

🤖 Model 📝 → 🖼️

ellen-arch/maldonado

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

📝 → 🖼️ • lora-person • text-to-image • image-to-image • 499 runs

🤖 Model 📝 → 🖼️

bcasey45/caseyyy

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

📝 → 🖼️ • text-to-image • lora-person • lora • 2.8K runs

🤖 Model 📝 → 🖼️

clovisviana-debug/mrclovis-lora

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

📝 → 🖼️ • lora-person • text-to-image • lora • 39 runs

🤖 Model 📝 → 🖼️

meowm30w/chrisc-lora

Generate front-facing headshot images of a person called chrisconnell from text prompts, intended for YouTube thumbnails...

📝 → 🖼️ • text-to-image • lora-person • headshot • 847 runs

🤖 Model 📝 → 🖼️

charliekclark/charlie-headshots

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

📝 → 🖼️ • lora-person • text-to-image • lora • 205 runs

🤖 Model 📝 → 🖼️

killjasper/jazzclone

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

📝 → 🖼️ • text-to-image • lora-person • lora • 28 runs

🤖 Model 📝 → 🖼️

carlaluiza10/carlaluiza

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

📝 → 🖼️ • lora-person • text-to-image • lora • 253 runs

🤖 Model 📝 → 🖼️

reikaclaudia/claudiaaurum_flux

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

📝 → 🖼️ • lora-person • text-to-image • image-to-image • 9 runs

🤖 Model 📝 → 🖼️

zeg06/arthur

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

📝 → 🖼️ • text-to-image • lora-person • lora • 193 runs

🤖 Model 📝 → 🖼️

vcollos/clovis

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

📝 → 🖼️ • text-to-image • lora-person • lora • 39 runs

🤖 Model 📝 → 🖼️

andrei907/andre

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

📝 → 🖼️ • text-to-image • lora-person • lora • 206 runs

🤖 Model 📝 → 🖼️

anywheretower/hermanoscorrea

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

📝 → 🖼️ • text-to-image • lora-person • lora • 185 runs

🤖 Model 📝 → 🖼️

stability-ai/stable-diffusion

Generate photo-realistic images from text prompts. Configure size up to 1024x1024, number of outputs (1–4), inference st...

📝 → 🖼️ • text-to-image • 110.8M runs