pftq / SkyReels-V2_ImprovementsLinks
SkyReels-V2 with batch mode, video input (extend existing videos), and multiple prompts.
☆13Updated last month
Alternatives and similar repositories for SkyReels-V2_Improvements
Users that are interested in SkyReels-V2_Improvements are comparing it to the libraries listed below
Sorting:
- Unofficial extension implementation of CausVid☆36Updated 2 months ago
- Extended Musubi Tuner with latent previews, fp16 accumulation, advanced cfg scheduling and more☆20Updated this week
- ☆80Updated 3 months ago
- ☆80Updated 3 weeks ago
- [ICCV 2025] Pytorch implementation of "PersonaCraft: Personalized Full-Body Image Synthesis for Multiple Identities from Single Reference…☆48Updated 3 months ago
- Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis (ICCV, 2025)☆51Updated this week
- MoD Control Tile Upscaler for SDXL Pipeline☆59Updated 3 months ago
- [CVPR 2025] Official implementation of the paper "Generative Inbetweening through Frame-wise Conditions-Driven Video Generation"☆93Updated 4 months ago
- [ICML 2025] Official PyTorch implementation of paper "Ultra-Resolution Adaptation with Ease".☆99Updated last month
- Pytorch implementation of Towards Consistent and Controllable Image Synthesis for Face Editing☆57Updated 2 months ago
- This repository contains the code for training FLUX.1-Fill-dev.☆20Updated 3 months ago
- Lora traing script for Lightricks LTX-video☆59Updated 4 months ago
- musubi-tuner modified to tune image2video/video infilling☆32Updated 5 months ago
- [Arxiv 2024] Edicho: Consistent Image Editing in the Wild☆117Updated 5 months ago
- ☆98Updated 2 months ago
- Set of auxiliary tools to use with image and video generation libaries. Mainly created to be used with diffusers☆57Updated last week
- Custom LORA training on DynamiCrafter☆18Updated 11 months ago
- Vid Driven Portrait Animation 🤢😷☆18Updated 11 months ago
- Official implementation of "Normalized Attention Guidance"☆88Updated this week
- Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".☆176Updated 2 months ago
- CogVideoX-LoRAs is a centralized repository for all LoRA models created for CogVideoX, filling the gap for a unified sharing space. With …☆80Updated 6 months ago
- VanGogh: A Unified Multimodal Diffusion-based Framework for Video Colorization☆14Updated 5 months ago
- This respository contains the code for the NeurIPS 2024 paper SF-V: Single Forward Video Generation Model.☆97Updated 7 months ago
- Official implementation of "Perturbed-Attention Guidance"☆56Updated 11 months ago
- ObjectClear: Complete Object Removal via Object-Effect Attention☆125Updated 2 weeks ago
- Implementation of paper: Flux Already Knows – Activating Subject-Driven Image Generation without Training☆37Updated last month
- ☆87Updated 2 months ago
- FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation☆64Updated last month
- Official code of "Edit Transfer: Learning Image Editing via Vision In-Context Relations"☆79Updated 3 weeks ago
- ☆44Updated 2 months ago