text-to-image AI Models

🤖 Model 📝 → 🖼️

upstateautomate/wikidiki

Generate NSFW, influencer/Instagram-style glamour images from text prompts. Optionally transform existing images or appl...

📝 → 🖼️ • text-to-image • image-to-image • nsfw • 3 runs

🤖 Model 📝 → 🖼️

fofr/sdxl-jwst

Generate JWST-style astrophotography from a text prompt. Optionally provide an input image for image-to-image conversion...

📝 → 🖼️ • text-to-image • image-to-image • astrophotography • 420 runs

🤖 Model 📝 → 🖼️

royronit/planetnesa

Generate cosmic, sci‑fi images from a text prompt. Optionally condition on an input image for image-to-image translation...

📝 → 🖼️ • text-to-image • image-to-image • image-inpainting • 18 runs

🤖 Model 📝 → 🖼️

loldoors/alien01

Generate images of an alien character called 4l1en01 from text prompts. Optionally transform or inpaint existing images...

📝 → 🖼️ • text-to-image • image-to-image • alien • 16 runs

🤖 Model 📝 → 🖼️

black-forest-labs/flux-2-flex

Generates and edits images from text prompts with adjustable quality-speed control and support for up to ten reference i...

📝 → 🖼️ • text-to-image • image-editing • image-to-image • 327.7K runs

🤖 Model 📝 → 🖼️

prunaai/ernie-image

Generate images from a text prompt. Enable an optional built-in prompt enhancer to expand short inputs into richer struc...

📝 → 🖼️ • text-to-image • text-rendering • 3 runs

🤖 Model 📝 → 🖼️

prunaai/ernie-image-turbo

Generate images from text prompts. Accepts a prompt with optional width/height (up to 2048), seed for reproducibility, a...

📝 → 🖼️ • text-to-image • text-rendering • 10 runs

🤖 Model 📝 → 🖼️

openai/gpt-image-2

Generates images from text prompts with strong instruction following, sharp text rendering, and detailed editing capabil...

📝 → 🖼️ • text-to-image • image-editing • image-style-transfer • 5.7M runs

🤖 Model 📝 → 🖼️

resilientcoders/pokemon-trainers

Generates images of Pokemon trainers based on text prompts. The trigger word for this LoRA fine-tune is 'poke-trainers'.

📝 → 🖼️ • text-to-image • lora • 17 runs

🤖 Model 📝 → 🖼️

marcodemutiis/fleece

Generates images featuring fleece fabric or fleece-related textures based on text prompts. The trigger word for this LoR...

📝 → 🖼️ • text-to-image • lora • 57 runs

🤖 Model 📝 → 🖼️

ultracoderru/nova-anime-xl-17

Generates anime-style images from text prompts using Danbooru tags. Specializes in creating anime, 2.5D, and 3D characte...

📝 → 🖼️ • text-to-image • anime • 2.8K runs

🤖 Model 📝 → 🖼️

ultracoderru/nova-anime-xl-il-140

Generate anime-style images from text prompts using Danbooru tags. Specializes in producing high-quality anime, 2.5D, an...

📝 → 🖼️ • text-to-image • anime • 350 runs

🤖 Model 📝 → 🖼️

marcodemutiis/cheap-vintage

Generates images with a cheap vintage aesthetic based on textual prompts. The trigger word for this LoRA fine-tune is 'c...

📝 → 🖼️ • text-to-image • lora • vintage • 33 runs

🤖 Model 📝 → 🖼️

ultracoderru/nova-anime-xl-14

Generates anime-style images from text prompts using Danbooru tag format. Optimized for anime and manga art styles with...

📝 → 🖼️ • text-to-image • anime • 469 runs

🤖 Model 📝 → 🖼️

marcodemutiis/animal-crossing

Generates images in the Animal Crossing video game art style based on text prompts. The trigger word for this LoRA fine-...

📝 → 🖼️ • text-to-image • lora • animal-crossing • 18 runs

🤖 Model 📝 → 🖼️

rossjillian/controlnet_2-1

Generate images from text prompts while maintaining the structural composition of an input image using ControlNet with S...

📝 → 🖼️ • image-to-image • text-to-image • 21.2K runs

🤖 Model 📝 → 🖼️

rossjillian/controlnet

Generates images from text prompts using Stable Diffusion with ControlNet conditioning to maintain the structural layout...

📝 → 🖼️ • image-to-image • text-to-image • 7.7M runs

🤖 Model 📝 → 🖼️

joezboom/yossiimages

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

📝 → 🖼️ • text-to-image • lora • lora-person • 161 runs

🤖 Model 📝 → 🖼️

jaime-owwo/owwo

Generates images in the OWWO brand style, producing porcelain minimalist worlds based on text prompts. The trigger word...

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

🤖 Model 📝 → 🖼️

crossnoir2023/lgeisha

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

📝 → 🖼️ • text-to-image • lora-person • lora • 177 runs