[论文速览]FreeU: Free Lunch in Diffusion U-Net[2309.11497]
发布人
打开封面 下载高清视频 观看高清视频 视频下载器
...
FreeU: Free Lunch in Diffusion U-Net —— 在多个diffusion模型上带来显著提升
...
FreeU: Free Lunch in Diffusion U-Net
...
扩散模型 - Diffusion Model【李宏毅2023】
...
[论文速览]LLaVA: Visual Instruction Tuning[2304.08485]
...
逐步蒸馏 Progressive Distillation
...
FreeU,优化unet权重缩放比例获得更好画面表现效果。目前已有插件可安装。
...
试了下siggraph 2023最佳论文3D 3d gaussian splatting,效果太好了，比现有的各种nerf更精细了。可以说是ai 3d方面的革…
...
[论文简析]CLIP Dense Inference Yields Open-Vocab ... For-Free[2309.14289]
...
【论文一刻】ICCV'23 Oral：可控人物图像生成方法-HUMAN SD
...
[论文速览]Diffusion Policy: Visuomotor Policy Learning via Action Diff.[2303.04137]
...
免费的午餐【 FreeU.插件功能性解读】Fooocus & MRE共同推广的好工具【强大而且免费】ai绘画工具
...
新插件FreeU，大幅改善你的AI图像渲染效果
...
【COMFYUI周报9.25】率先支持FreeU! 以及上限更高的自由搭配任意工作流
...
【论文精读】Dreambooth：diffusion生成模型微调方法
...
[论文速览]LongLoRA: Efficient Fine-tuning of Long-Context LLMs[2309.12307]
...
[论文速览]Implicit Behavioral Cloning / IBC[2109.00137]
...
[论文速览]LoRA: Low-Rank Adaptation of Large Language Models[2106.09685]
...
超级水刊，几乎不退稿的计算机3区sci
...
[论文速览]RetNet: A Successor to Transformer for Large Language Models[2307.08621]
...
RetNet算法介绍，它真的能继承Transformer？
...
[论文速览]Structured Denoising Diffusion Models in Discrete State-Spaces[2107.03006]
...
[论文简析]Vision Transformers Need Registers[2309.16588]
...
[论文速览]MixUp: Beyond Empirical Risk Minimization[1710.09412]
...
[论文速览]Open-vocabulary Object Segmentation with Diffusion Models[2301.05221]
...
[论文简析]Contrastive Language, Action, and State Pre-training...[2304.10782]
...
[论文简析]DiffSeg: Unsupervised Zero-Shot Seg. using Stable Diffusion[2308.12469]
...
[论文夕拾]Diffusion Models for Robotics
...
[论文夕拾]Mixed Sample Data Augmentations, Part 1
...
[论文速览]Denoising Diffusion Implicit Models / DDIM[2010.02502]
...
[论文速览]Scalable Video Object Segmentation with Simplified Framework[2308.09903]
...
[论文简析]Region-Aware Pretraining for Open-Vocab. Object Det. w/ ViT[2305.07011]
...
[论文简析]Visual Autoregressive Modeling: ...via Next-Scale Prediction[2404.02905]
...
[论文速览]Drag Your GAN: Interactive Point-based Manipulation...[2305.10973]
...
[论文速览]RegMixup: Mixup as a Regularizer Can Surprisingly Improve...[2206.14502]
...
[论文简析]DropPos: Pre-Training ViTs by Reconstructing Dropped Positions[2309.03576]
...
[论文速览]Finite Scalar Quantization: VQ-VAE Made Simple[2309.15505]
...
[论文简析]Crossway Diffusion: Improving Diffusion-based ... via SSL[2307.01849]
...
[论文简析]DreamBooth: Fine Tuning Text-to-Image Diffusion Models...[2208.12242]
...
[论文简析]Patching Open-Vocabulary Models by Interpolating Weights[2208.05592]
...
[论文简析]BiFormer: Vision Transformer with Bi-Level Routing Attention[2303.08810]