Alternatives and similar repositories for ST-MFNet

Users that are interested in ST-MFNet are comparing it to the libraries listed below

• rynmurdock / inanimate
  Generate images from an initial frame and text
  ☆37Updated 2 years ago
• XmYx / tinyvae-flux
  ☆33Updated last year
• camenduru / ExVideo-jupyter
  ☆14Updated last year
• jbilcke-hf / VideoModelStudio
  [NOTE] I do not have enough ressources to maintain VMS, please use Ostris's AI-Tookit instead
  ☆42Updated 2 months ago
• viddle-app / animatediff
  Animatediff implementation. Includes a ControlNet pipeline.
  ☆19Updated last year
• CiaraStrawberry / stylecodes
  ☆46Updated 3 weeks ago
• dajes / AnimateDiff
  implementation of AnimateDiff.
  ☆32Updated 2 years ago
• LucipherDev / Flux.1-dev-PuLID-jupyter
  Jupyter notebooks for PuLID face transfer with Flux.1 dev. Able to run on Google Colab Free Tier
  ☆18Updated 11 months ago
• hannahun1 / anodes
  ☆16Updated last year
• MrForExample / FlexiSyncMVD
  ☆19Updated 7 months ago
• camenduru / AnimateDiff-Lightning-jupyter
  ☆23Updated last year
• camenduru / Animefy
  Animefy: ComfyUI workflow designed to convert images or videos into an anime-like style automatically.
  ☆22Updated last year
• camenduru / TANGO-jupyter
  ☆13Updated last year
• brianfitzgerald / Comfy-SVDTools
  ☆43Updated last year
• camenduru / MotionCtrl-colab
  ☆17Updated last year
• ethansmith2000 / StableTwoUnet
  ☆26Updated last year
• ExponentialML / ComfyUI_LiveDirector
  Experimental method to use reference video to drive motion in generations without training in ComfyUI.
  ☆37Updated last year
• sdbds / florence2-ft-advanced
  finetune your florence2 model easy
  ☆21Updated last year
• itsmag11 / Omegance
  Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (ICCV, 2025)
  ☆52Updated 2 months ago
• camenduru / mimic-motion-tost
  ☆23Updated last year
• camenduru / sliders-colab
  ☆32Updated last year
• camenduru / MotionDirector-colab
  ☆16Updated 2 years ago
• LucipherDev / Flux.1-dev-ControlNet-jupyter
  ControlNet with Txt2Img | Img2Img | + Multiple LoRAs, All in one jupyter notebook for Flux.1 dev. Able to run on Google Colab Free Tier
  ☆20Updated last year
• LambdaLabsML / Open-Sora
  Open-Sora: Democratizing Efficient Video Production for All
  ☆19Updated last year
• korakoe / VALL-E-X
  An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io
  ☆16Updated last year
• Apple-jun / FilmComposer
  Music production for silent film clips.
  ☆29Updated 7 months ago
• siso-paper / SISO
  Official implementation of "Single Image Iterative Subject-driven Generation and Editing".
  ☆101Updated 6 months ago
• camenduru / VisualStylePrompting-jupyter
  ☆13Updated last year
• zsxkib / cog-comfyui-hunyuan-video
  ☆17Updated 10 months ago
• agentic-learning-ai-lab / procreate-diffusion
  Public code release for the paper "ProCreate, Don’t Reproduce! Propulsive Energy Diffusion for Creative Generation"
  ☆41Updated last week