
jagilley/controlnet-scribble
Generate images from a hand-drawn sketch and a text prompt. Condition Stable Diffusion with ControlNet (scribble) to fol...
Found 31 models (showing 1-20)
Generate images from a hand-drawn sketch and a text prompt. Condition Stable Diffusion with ControlNet (scribble) to fol...
Edit images from text instructions using one to three reference images, outputting edited image(s). Combine multiple inp...
Generate stylized QR code artwork from a text prompt and QR content. Embed a scannable QR pattern into 3D-styled scenes...
Apply a reference image’s style to a new subject and generate an image guided by text and ControlNet. Takes a text promp...
Generate images from a text prompt guided by the human pose in an input image. Provide an image with a person and a prom...
Generate images from a text prompt while controlling composition with an input image using ControlNet. Condition generat...
Generate animated video from a short control video or GIF and text prompts. Guide motion with AnimateDiff Prompt Travel...
Generate images from a text prompt guided by a reference pose image. Use SDXL with ControlNet OpenPose to extract human...
Fill masked regions of an image from a text prompt. Accepts an input image (control image), a mask, and a prompt, then u...
Replace backgrounds in images using Stable Diffusion and ControlNet. Input an image and a textual prompt to generate a n...
Generate images from multilingual text prompts. Leverage a latent diffusion pipeline with a CLIP-ViT-G encoder for stron...
Colorizes line art images using ControlNet, focusing on anime-style illustrations. Accepts a line art input image and ge...
Generate images from prompts or transform images with SDXL using Canny ControlNet and optional LoRA adapters. Accept a t...
Generate realistic images from text prompts using the sd-webui API with support for ControlNet canny API. This model lev...
Generate stylized, scannable QR code images from a URL and a text prompt. Leverage ControlNet trained on Stable Diffusio...
Edit images from a text prompt while preserving the source layout with ControlNet guidance. Provide an input image and a...
Generate images from visual inputs without text prompts. Provide an input image and a control map and produce a new imag...
Generate stylized images from a reference image and text prompt. Condition generation with control types such as pose, c...
Generate stylized, scannable QR codes from a text prompt and target content (URL or text). Leverage Stable Diffusion wit...
Generate images from an input image and text prompt with normal-map guidance. Use ControlNet to condition Stable Diffusi...