
jagilley/controlnet-hed
Transform an input image based on a text prompt while preserving its structure using HED edge maps. Accepts an image and...
Found 73 models (showing 61-73)
Transform an input image based on a text prompt while preserving its structure using HED edge maps. Accepts an image and...
Edit images from a text instruction and output an edited image. Support both low-level appearance edits (adding, removin...
Perform virtual try-on from images: take a person photo, a reference outfit/style image, and an optional background imag...
Generate GTA Vβstyle images from a text prompt, with optional image-to-image transformation. Apply LoRA weights by suppl...
Edit images with depth-aware control using a text prompt and a control image, preserving 3D structure, perspective, and...
Convert a person photo into an anime-style image. Takes an input image of a person and outputs a stylized anime portrait...
Translate images between visual domains using a content image and a style reference image, outputting a single translate...
Convert face photos or videos into anime-style images or videos. Accept a single image or short video and perform image-...
Generate vintage US National Park posterβstyle images from text prompts. Stylize existing images (image-to-image) and in...
Generate stylized images from a reference photo and a text prompt. Provide one to four input images to preserve identity...
Edit photos by transferring the style or texture from a reference image onto a specified object or surface. Takes an inp...
Generate images from text prompts with precise text rendering and style control. Accept an optional image and mask to in...
Generate images from text prompts at high speed. Optionally guide composition with an image reference, transfer visual s...