mit-han-lab/fastcomposer

FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention

PythonShell
This is stars and forks stats for /mit-han-lab/fastcomposer repository. As of 01 May, 2024 this repository has 487 stars and 25 forks.

FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention [website] [demo][replicate api] Abstract Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods struggle with multi-subject generation as they often blend features among subjects....
Read on GithubGithub Stats Page
repotechsstarsweeklyforksweekly
THUDM/VisualGLM-6BPythonShell3.4k03480
iryna-kondr/scikit-llmPython2.6k+12210+2
Syan-Lin/CyberWaifuPython85501010
renode/renodeRobotFrameworkC#Python1.3k+8227+2
beeper/beepberryShell401+2320
Ilya114/Box64DroidShell5040360
sdeleuze/spring-boot-crac-demoJavaShellDockerfile530120
qt/qt5ShellPowerShellCMake1.3k05840
martinpitt/umockdevValaCShell276+1460
nonoDevil/vim_confVim ScriptPythonOther0000