SDXL fine-tuned on upside down photos of people

Detecting Twenty-thousand Classes using Image-level Supervision

testing dreambooth on self

Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder

SDXL fine tuned on Genshin Impact landscape by imageapp.xyz

ProteusV0.1 uses OpenDalleV1.1 as a base and further refines prompt adherence and stylistic capabilities to a measurable degree

Semantic Room Wireframe

Just an experiment. Nothing new here.

Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house

🦙 LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions

Nous Hermes 2 Mixtral 8x7B DPO is a Nous Research model trained over the Mixtral 8x7B MoE LLM

Create driving poses for magic-animate

Hermes 2 Pro is an updated and cleaned version of the OpenHermes 2.5 Dataset, as well as a newly introduced Function Calling and JSON Mode dataset developed in-house

SDXL fine-tuned on Pixar Cars

Use a face to instantly make images. Uses SDXL Lightning checkpoints.

DreamShaper V8 Model (Text2Img, Img2Img and Inpainting)

Turn anything into an abstract fine art masterpiece 🎨

Gorilla: Large Language Model Connected with Massive APIs

Easy video inpainting using only a mask of the first video frame

Super-resolves an LR video frame (ultra-wide) using a reference video frame (wide-angle)