BestHub
Sign in
Tag

AI Painting

0 views collected around this technical thread.

360 Tech Engineering
360 Tech Engineering
Oct 31, 2024 · Artificial Intelligence

HiCo: Hierarchical Controllable Diffusion Model for Layout-to-Image Generation

The paper introduces HiCo, a hierarchical controllable diffusion model that enables precise layout‑to‑image generation by decoupling object and background features through weight‑shared branches and a fusion module, achieving high‑quality results and efficient inference as demonstrated on the HiCo‑7K benchmark.

AI PaintingHiCoImage Generation
0 likes · 9 min read
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-Image Generation
Rare Earth Juejin Tech Community
Rare Earth Juejin Tech Community
Feb 4, 2024 · Artificial Intelligence

Understanding Stable Diffusion Architecture and Implementing It with the Diffusers Library

This article reviews the evolution from GANs to diffusion models, explains the components of Stable Diffusion—including the CLIP text encoder, VAE, and UNet—and provides step‑by‑step Python code using HuggingFace's Diffusers library to generate images from text prompts.

AI PaintingPythonStable Diffusion
0 likes · 12 min read
Understanding Stable Diffusion Architecture and Implementing It with the Diffusers Library
php中文网 Courses
php中文网 Courses
Sep 19, 2023 · Artificial Intelligence

Integrating Midjourney AI Painting API with PHP: A Step-by-Step Guide

This tutorial explains how to use PHP to connect to Midjourney's AI painting API, covering preparation, request construction, cURL transmission, response handling, and a complete example that enables developers to generate and manage AI‑created artwork.

AI PaintingAPI IntegrationArtificial Intelligence
0 likes · 6 min read
Integrating Midjourney AI Painting API with PHP: A Step-by-Step Guide
Tencent Cloud Developer
Tencent Cloud Developer
May 25, 2023 · Artificial Intelligence

QQGC: A Two-Stage Text-to-Image Model with Prior and Decoder Architectures for Efficient AI Painting

QQGC, Tencent’s two‑stage text‑to‑image model that separates CLIP‑based Prior mapping from a Stable Diffusion Decoder, leverages T5‑enhanced text embeddings and a suite of efficiency tricks—including FP16, flash attention, ZeRO and GPU‑RDMA—to train over‑2 B‑parameter models on 64 GPUs, achieving state‑of‑the‑art FID and CLIP scores while supporting image variation, semantic img2img, precise CLIP‑vector edits and unsafe‑content filtering, and now powers the company’s Magic Painting Room.

AI PaintingCLIP embeddingTraining Acceleration
0 likes · 12 min read
QQGC: A Two-Stage Text-to-Image Model with Prior and Decoder Architectures for Efficient AI Painting