text-to-image AI Models

🤖 Model 📝 → 🖼️

jyoung105/auraflow-v2

Generate images from text prompts. Leverage a fully open-source, flow-based text-to-image architecture for efficient sam...

📝 → 🖼️ • text-to-image • flow-matching • 30 runs

🤖 Model 📝 → 🖼️

jyoung105/perflow

Generate images from text prompts with SDXL accelerated by PeRFlow (Piecewise Rectified Flow), a plug-and-play flow samp...

📝 → 🖼️ • text-to-image • sdxl • rectified-flow • 17 runs

🤖 Model 📝 → 🖼️

0xdeadd/bijay

Generate images from text prompts. Optionally transform an input image (img2img) or fill masked regions for inpainting....

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 26 runs

🤖 Model 📝 → 🖼️

odetonoise/daveface-loraflow

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

📝 → 🖼️ • text-to-image • lora-person • lora • 169 runs

🤖 Model 📝 → 🖼️

jayenkai/derek

Generates images of a cartoon character called Derek based on text prompts. The trigger word for this LoRA fine-tune is...

📝 → 🖼️ • lora-person • text-to-image • cartoon • 927 runs

🤖 Model 📝 → 🖼️

yuezheng2006/flux-dev-jaychow

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

📝 → 🖼️ • text-to-image • lora-person • lora • 56 runs

🤖 Model 📝 → 🖼️

marcodemutiis/minimal_liminal

Generate liminal-space style images from text prompts. Optionally provide an input image for image-to-image translation...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 131 runs

🤖 Model 📝 → 🖼️

usamaehsan/multi-controlnet-x-ip-adapter-vision-v2

Generate images from a text prompt, with optional structure and style control via ControlNet and IP-Adapter. Accepts a p...

📝 → 🖼️ • text-to-image • sketch-to-image • image-inpainting • 5.1K runs

🤖 Model 📝 → 🖼️

aisha-ai-official/pony-realism-v2.2

Generates realistic images from text prompts using the Pony-Realism v2.2 model. Features multiple scheduler options incl...

📝 → 🖼️ • text-to-image • 171.5K runs

🤖 Model 📝 → 🖼️

usamaehsan/controlnet-x-ip-adapter-realistic-vision-v5

Generate images from text, with optional image-to-image translation and inpainting, using multi-ControlNet and IP-Adapte...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 658.9K runs

🤖 Model 📝 → 🖼️

heedster/realistic-vision-v5

Generate photorealistic images from text prompts. Accepts a prompt with optional negative prompt, seed, steps, and resol...

📝 → 🖼️ • text-to-image • photorealistic • 1.2M runs

🤖 Model 📝 → 🖼️

cloneofsimo/realistic_vision_v1.3

Generate photo-realistic images from text prompts using the Realistic Vision v1.3 model. Supports text-to-image generati...

📝 → 🖼️ • text-to-image • image-to-image • 564.2K runs

🤖 Model 📝 → 🖼️

lucataco/realvisxl-v2.0

Generate photorealistic images from text prompts, with optional image-to-image translation and masked inpainting. Levera...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 288.3K runs

🤖 Model 📝 → 🖼️

afterpeak/flux-slowed

Generate album/cover-art style images in the slowed + reverb music aesthetic from a text prompt. Optionally transform an...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 7.2K runs

🤖 Model 📝 → 🖼️

fofr/flux-cyberpunk-typeface

Generate cyberpunk-style typography and wordmarks from text prompts. Optionally use an input image or mask for image-to-...

📝 → 🖼️ • text-to-image • image-to-image • typography • 882 runs

🤖 Model 📝 → 🖼️

oliverobenrauch/ai-watchultra

Generate images of a smartwatch called AIWATCHULTRA from text prompts. Optionally use an input image and mask for image-...

📝 → 🖼️ • text-to-image • image-inpainting • smartwatch • 9 runs

🤖 Model 📝 → 🖼️

brandnexus/metarb

Generate images of MetaRB smart glasses from text prompts. Transform existing photos or inpaint masked regions to add or...

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

🤖 Model 📝 → 🖼️

bah23-sys/l-nan-wind

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 • lora-person • 92 runs

🤖 Model 📝 → 🖼️

asiryan/kandinsky-3.0

Generate images from text prompts or transform an input image with image-to-image. Accepts a prompt and optionally an im...

📝 → 🖼️ • text-to-image • image-to-image • 111.4K runs

🤖 Model 📝 → 🖼️

jack000/glid-3-xl

Generates images from textual prompts using a 1.4B parameter latent diffusion model. Supports tasks like inpainting and...

📝 → 🖼️ • text-to-image • image-generation • inpainting • 45.5K runs