Decoding Micromotion in Low-dimensional Latent Spaces from StyleGAN

Canny, soft edge, depth, lineart, segmentation, pose, etc

Applies various image effects and transformations to enhance and manipulate images.

A Ma.K Maschinen Krieger Suit model

RESEARCH/NON-COMMERCIAL USE ONLY: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models

StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators

Implementation of SDXL RealVisXL_V2.0 img2img

SDXL fine-tuned on the people in Toy Story (1995)

SDXL Model (Text2Img, Img2Img and Inpainting)

Tesla Model 3 Highland SDXL fine-tune

Depth Anything on full video files

Fast Segmind-Vega with 2-8 inference steps.

An open-source model for program synthesis. Competitive with OpenAI Codex.

VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing in the Wild

Source: fblgit/juanako-7b-UNA ✦ Quant: TheBloke/juanako-7B-UNA-AWQ ✦ juanako uses UNA, Uniform Neural Alignment. A training technique that ease alignment between transformer layers yet to be published

Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

Apply the style of an image to your image. Upscaling with Clarity is recommended. Twitter/X: @philz1337x

High-Fidelity GAN Inversion for Image Attribute Editing

Turn an image into a set of images from different 3D angles

Kolors is a SOTA base image model for high quality image generation