Generate song ideas!

An SDXL fine-tune based on blueprints

Stable Diffusion fine-tuned of the Codex Borgia, a 16th century Meso-American manuscript.

Generates 3D assets from images

Train on RealVisXL 4.0 (Realistic Vision XL 4) | Mixed precision bf16 any LoRA

Virtual dressing room fullbody

Panoptic Scene Graph Generation

A language model by Google for tasks like classification, summarization, and more

Generates subtitles

Source: monology/openinstruct-mistral-7b ✦ Quant: TheBloke/openinstruct-mistral-7B-AWQ ✦ Commercially-usable 7B model, based on mistralai/Mistral-7B-v0.1 and finetuned on VMware/open-instruct

Intelligent image scaling to 4x resolution

Classifies images with ResNet-50

Shiba stable diffusion model

SDXL model trained on the game The Return of The Obra Dinn

(wip) Audiocraft is a library for audio processing and generation with deep learning.

Prompt Parrot generates text2image prompts from finetuned distilgpt2

Made public only for API calls. Use min-dalle instead-- it's superior.

(development branch) Inpainting for Stable Diffusion

🗣️ TalkNet-ASD: Detect who is speaking in a video

Text-guided image generation and editing