image-generation AI Models

🤖 Model 📝 → 🖼️

camenduru/story-diffusion

Generate anime-style images and comics from textual prompts and reference images. Supports various styles including Japa...

📝 → 🖼️ • image-generation • anime • comic-creation • 1.3K runs

🤖 Model 📝 → 🖼️

dribnet/pixray-text2pixel-0x42

Generates images from text prompts using the Pixray engine. Supports various aspect ratios including widescreen, square,...

📝 → 🖼️ • text-to-image • image-generation • pixray • 148.4K runs

🤖 Model 📝 → 🖼️

pagebrain/cyberrealistic-v3-3

Generate hyperrealistic and photorealistic portrait images from textual prompts. Supports img2img and inpainting modes w...

📝 → 🖼️ • text-to-image • image-generation • portrait-photography • 7.0K runs

🤖 Model 📝 → 🖼️

dribnet/clipit

Generates images from text prompts using a combination of CLIP and VQGAN or PixelDraw. Supports different aspect ratios...

📝 → 🖼️ • text-to-image • image-generation • vqgan • 6.7K runs

🤖 Model 📝 → 🖼️

bfirsh/vqgan-clip

Generates images from text prompts using VQGAN and CLIP. Allows customization through parameters like iterations, image...

📝 → 🖼️ • text-to-image • vqgan • clip • 6.6K runs

🤖 Model 📝 → 🖼️

cjwbw/clip-guided-diffusion-pokemon

Generate pixel art images of Pokémon from textual prompts using a diffusion model trained on Pokémon sprites.

📝 → 🖼️ • text-to-image • pixel-art • pokemon • 4.9K runs

🤖 Model 🔊

hohsiangwu/wav2clip

Generate images from audio inputs using Wav2CLIP and VQGAN-CLIP. This model processes audio files to create visual repre...

🔊 • audio-to-image • image-generation • vqgan-clip • 896 runs

🤖 Model 🎥

replicate/goo

Generate abstract, fluid goo visuals as still images or videos. Control animation speed, depth, and scale, set resolutio...

🎥 • video-generation • image-generation • procedural-animation • 212 runs

🤖 Model 🖼️ → 🖼️

zeke/haiku-image

Generate images with short text overlays, optionally deriving the background color from an input image. Accept an option...

🖼️ → 🖼️ • image-generation • image-to-image • 410 runs

🤖 Model 📝 → 🖼️

pagebrain/absolutereality-v1-6

Generate high-fantasy style images from textual prompts, featuring intricate details and a blend of realism and fantasy....

📝 → 🖼️ • text-to-image • img2img • inpainting • 953 runs

🤖 Model 📝 → 🖼️

pagebrain/lyriel-v1-6

Generate highly detailed and realistic images from textual prompts, with capabilities for img2img transformations and in...

📝 → 🖼️ • text-to-image • img2img • inpainting • 1.5K runs