TAAFT
Free mode
100% free
Freemium
Free Trial
Create tool
ModelsLatent Diffusion

Latent Diffusion

By CompVis
Image Gen 2
Released: April 1, 2022

Overview

No overview available.

Description

Efficient diffusion model; precursor to Stable Diffusion.

About CompVis

CompVis is a research group focusing on computer vision and deep learning.

Industry: Artificial Intelligence
Company Size: N/A
Location: Heidelberg, DE
Website: compvis
View Company Profile

Related Models

Gemini 2.5 Flash Image

Gemini 2.5 Flash Image is Google DeepMind’s lightweight vision–language model. It processes images alongside text prompts to deliver grounded answers, OCR, chart/diagram interpretation, and visual reasoning. Optimized for speed and efficiency, it’s ideal for real-time assistants and cost-sensitive multimodal applications.

Image New

Midjourney V6.1

Midjourney V6.1 refines V6 with crisper detail, better prompt fidelity, steadier hands and text, and more reliable identity/style consistency. It’s the “cleaner, sharper, more controllable” update for production-ready visuals.

Image New

StyleCLIP

No description available.

Image
Last updated: March 3, 2025