stable-diffusion AI Models

🤖 Model 📝 → 🖼️

bytedance/res-adapter

Generate images from text prompts at arbitrary resolutions and aspect ratios using a resolution adapter for Stable Diffu...

📝 → 🖼️ • text-to-image • resolution-adaptation • arbitrary-aspect-ratio • 1.4K runs

🤖 Model 📝 → 🖼️

cjwbw/stable-diffusion-high-resolution

Generate high-resolution images from text prompts. Use txt2imghd (GOBIG) with Real-ESRGAN upscaling and tiled img2img re...

📝 → 🖼️ • text-to-image • high-resolution • 73.0K runs

🤖 Model 🖼️

wolverinn/ecommerce-virtual-try-on

Generate virtual try-on images using Stable Diffusion and IP-Adapter from a face image and a commerce image containing c...

🖼️ • virtual-try-on • image-generation • ecommerce • 2.5K runs

🤖 Model 🖼️ → 🖼️

wolverinn/professional-faceshot

Generate professional face shots from an input image using Stable Diffusion and LoRA fine-tuning. This model focuses on...

🖼️ → 🖼️ • image-to-image • face-generation • photo-enhancement • 1.2K runs

🤖 Model 📝 → 🖼️

prunaai/stable-diffusion-cheetah

Generate one or more images from a text prompt. Use an optimized Stable Diffusion pipeline that runs about 3x faster and...

📝 → 🖼️ • text-to-image • speed-optimized • 190 runs

🤖 Model 📝 → 🖼️

pratos/stable-diffusion-2-1-512

Generates digital illustrations from textual prompts, producing whimsical and anthropomorphic characters with a friendly...

📝 → 🖼️ • text-to-image • digital-illustration • stable-diffusion • 9.4K runs

🤖 Model 🖼️ → 🖼️

wolverinn/realistic-background

Replace backgrounds in images using Stable Diffusion and ControlNet. Input an image and a textual prompt to generate a n...

🖼️ → 🖼️ • image-editing • background-replacement • stable-diffusion • 138.5K runs

🤖 Model 📝 → 🖼️

cjwbw/dreamshaper

Generate images from a text prompt. Produce artistic and photorealistic outputs, including digital paintings and illustr...

📝 → 🖼️ • text-to-image • 1.3M runs

🤖 Model 📝 → 📝

hellojixian/sd-promot-converter

Converts story paragraphs into Stable Diffusion prompts. Takes a text story as input and generates 4 different prompt su...

📝 → 📝 • text-generation • 42 runs

🤖 Model 🖼️ → 🖼️

wolverinn/simple-background

Replace image backgrounds using Stable Diffusion and ControlNet. Input an image to remove its background, generate a new...

🖼️ → 🖼️ • image-editing • background-replacement • stable-diffusion • 4.5K runs

🤖 Model 📝 → 📝

cjwbw/distilgpt2-stable-diffusion-v2

Generates descriptive prompts for Stable Diffusion image generation models from a starting text input. Uses a fine-tuned...

📝 → 📝 • text-generation • 609 runs

🤖 Model 🖼️

replicate/dreambooth

Train a personalized Stable Diffusion model from a small set of images. Provide a ZIP of subject or style images, an ins...

🖼️ • image-model-training • dreambooth • stable-diffusion • 296.2K runs

🤖 Model 🖼️

cloneofsimo/lora-training

Train LoRA adapters for Stable Diffusion from a ZIP of images with task presets for faces, objects, and styles. Takes a...

🖼️ • image-lora-training • stable-diffusion • 33.4K runs

🤖 Model 🖼️ → 📝

methexis-inc/img2prompt

Generates text prompts from input images that can be used with Stable Diffusion to recreate similar-looking versions of...

🖼️ → 📝 • image-to-text • 2.7M runs

🤖 Model 📝 → 🖼️

zeke/stable-diffusion

Generate images from a text prompt. Control size (up to 1024x768 or 768x1024), number of outputs (1–4), random seed, and...

📝 → 🖼️ • text-to-image • stable-diffusion • 1.3K runs

🤖 Model 📝 → 🖼️

cjwbw/taiyi-stable-diffusion-1b-chinese-v0.1

Generate images from Chinese text prompts. Takes a Chinese prompt with configurable image size, sampling steps, seed, an...

📝 → 🖼️ • text-to-image • chinese-language • 972 runs

🤖 Model 🖼️

lucataco/stable-diffusion-3.5-large-lora-trainer

Train DreamBooth LoRA adapters for Stable Diffusion 3.5 Large from a zip of training images and an instance prompt, outp...

🖼️ • image-lora-training • dreambooth • stable-diffusion • 758 runs

🤖 Model 🖼️

lucataco/train-text-to-image-lora

Trains LoRA (Low-Rank Adaptation) weights for Stable Diffusion text-to-image models including SDv1.4, SDv1.5, SDv2.0, an...

🖼️ • image-lora-training • 30 runs