Phantom-video / PhantomLinks
Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment
β1,056Updated this week
Alternatives and similar repositories for Phantom
Users that are interested in Phantom are comparing it to the libraries listed below
Sorting:
- π₯π₯ UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioningβ1,075Updated last month
- β972Updated 2 weeks ago
- FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesisβ1,288Updated 2 weeks ago
- πΉ A more flexible framework that can generate videos at any resolution and creates videos from images.β1,032Updated this week
- β1,137Updated last month
- SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformersβ511Updated last month
- β745Updated 3 months ago
- HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generationβ962Updated 2 weeks ago
- Lumina-Image 2.0: A Unified and Efficient Image Generative Frameworkβ714Updated this week
- β783Updated 6 months ago
- A pipeline parallel training script for diffusion models.β1,086Updated this week
- Enhance-A-Video: Better Generated Video for Freeβ526Updated 2 months ago
- HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideoβ1,460Updated last week
- Illumination Drawing Tools for Text-to-Image Diffusion Modelsβ761Updated 3 weeks ago
- The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noβ¦β905Updated this week
- Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Training released! Surpasses GPT-4o in ID persistenβ¦β1,565Updated 2 weeks ago
- Official repository of In-Context LoRA for Diffusion Transformersβ1,885Updated 5 months ago
- A minimal and universal controller for FLUX.1.β1,587Updated 2 weeks ago
- β508Updated last month
- A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemβ¦β1,326Updated this week
- β704Updated 6 months ago
- Official implementations for paper: VACE: All-in-One Video Creation and Editingβ2,273Updated 2 weeks ago
- β403Updated this week
- β520Updated 4 months ago
- β685Updated this week
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelβ833Updated last week
- β1,488Updated 3 months ago
- ACTalker: an end-to-end video diffusion framework for talking head synthesis that supports both single and multi-signal control (e.g., auβ¦β273Updated last month
- β559Updated this week
- This node provides lip-sync capabilities in ComfyUI using ByteDance's LatentSync model. It allows you to synchronize video lips with audiβ¦β794Updated last week