福模

免费开源AI模型下载_本地AI工具资源平台

生成模型Generative Models

ControlNet条件控制模型 - 精确控制AI图像生成

ControlNet Conditional Control Model - Precise Control of AI Image Generation

ControlNet条件控制模型,实现精确控制AI图像生成的模型。通过额外的条件输入,如边缘图、姿态图等,可以精确控制生成图像的结构和布局,提升生成结果的可控性。

ControlNet conditional control model, a model achieving precise control of AI image generation. Through additional conditional inputs, such as edge maps, pose diagrams, etc., it enables precise control of the structure and layout of generated images, enhancing the controllability of generation results.

ControlNet条件控制图像生成结构控制ControlNetConditional ControlImage GenerationStructure Control

文件大小

15.2 GB

Upload Size

15.2 GB

上传日期

2024-12-22

Upload Date

2024-12-22

下载次数

19,600

Downloads

19,600

评分

4.9/5.0

Rating

4.9/5.0

下载资源 Download Resources

下载资源表示您同意我们的使用条款和隐私政策

By downloading this resource, you agree to our Terms of Service and Privacy Policy

相关资源推荐

Imagen AI图像生成模型 - 高保真文本到图像合成Imagen AI Image Generation Model - High-Fidelity Text-to-Image Synthesis

Imagen AI图像生成模型,基于扩散模型的高保真文本到图像合成系统。能够生成高质量、高分辨率的图像,匹配文本描述的细节。

Imagen AI image generation model, a high-fidelity text-to-image synthesis system based on diffusion models. Capable of generating high-quality, high-resolution images matching the details of text descriptions.

Imagen图像生成文本到图像ImagenImage GenerationText-to-Image
16.5 GB2025-02-09
GLIDE文本到图像AI模型 - 低分辨率扩散模型GLIDE Text-to-Image AI Model - Low-Resolution Diffusion Model

GLIDE文本到图像AI模型,低分辨率扩散模型,支持文本引导的图像生成。通过CLIP引导实现精确的图像生成,平衡质量与效率。

GLIDE text-to-image AI model, a low-resolution diffusion model supporting text-guided image generation. Achieves precise image generation through CLIP guidance, balancing quality with efficiency.

GLIDE文本到图像扩散模型GLIDEText-to-ImageDiffusion Model
13.4 GB2025-02-15
VQGAN图像生成模型 - 高质量图像合成与风格迁移VQGAN Image Generation Model - High-Quality Image Synthesis and Style Transfer

VQGAN图像生成模型,实现高质量图像合成与风格迁移。结合了变分自编码器和生成对抗网络的优势,能够在保持细节的同时实现多样化的艺术风格转化。

VQGAN image generation model, achieving high-quality image synthesis and style transfer. Combining the advantages of variational autoencoders and generative adversarial networks, it enables diverse artistic style transformations while preserving details.

VQGAN图像生成风格迁移VQGANImage GenerationStyle Transfer
10.5 GB2024-12-18