Sources & links related to AInVFX news episodes
ComfyUI doesn't have to be overwhelming. This comprehensive guide takes you from manual installation through creating your first complete AI workflowβimage generation, multi-angle art direction, video creation, post-processing, and HD upscaling. Everything you need to go from beginner to confident.
π Resources:
ComfyUI:
Installation Prerequisites:
- Python 3.13 β’ UV Package Manager β’ Git
- NVIDIA Drivers β’ PyTorch
Tools & Nodes Featured:
- Z-Image β’ QwenImageEdit β’ Kandinsky-5
- KJ Nodes β’ SeedVR2 VideoUpscaler
Related Tutorials:
π° Read the full article: Demystifying ComfyUI: Complete installation to production workflow guide
After 4 months of community-driven development, SeedVR2 v2.5 brings a complete architectural redesign. New 4-node system, GGUF quantization for 8GB GPUs, torch.compile optimization, native alpha support, and production-ready CLI make professional upscaling accessible to everyone. Breaking change but worth it.
π ComfyUI Workflows & Assets: Directly in the ComfyUI Template Manager or at https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler/tree/main/example_workflows
π Resources:
SeedVR2 Implementation:
Model Repositories:
SeedVR2 Research:
π° Read the full article: SeedVR2 v2.5: The complete redesign that makes 7B models run on 8GB GPUs
π€Ώ One-Step Video Upscaling: Complete ComfyUI SeedVR2 Guide (Free workflow included) | AInVFX July 11
ByteDance's SeedVR2 transforms video upscaling with one-step restoration instead of 15-50. Complete tutorial covering ComfyUI setup, BlockSwap for consumer GPUs, alpha channel workflows, and multi-GPU processing.
π ComfyUI Workflows & Assets: episodes/20250711
π Resources:
SeedVR2 Research:
ComfyUI Implementation:
- ComfyUI-SeedVR2_VideoUpscaler by NumZ
- ComfyUI-CoCoTools_IO by Conor-Collins
- ComfyUI-VideoHelperSuite by Kosinkadink
π° Read the full article: One-step 4K video upscaling and beyond for free in ComfyUI with SeedVR2
π¬ Speed up WAN 2-3x with MagCache + NAG negative prompting + One-step upscale | AInVFX News June 21
Four practical techniques for faster, better video generation: MagCache accelerates diffusion 2-3x, NAG brings back negative prompting to distilled models, DLoRAL upscales videos in one step, and MIT shows how AI can be use for Art restoration.
π ComfyUI Workflows & Assets: episodes/20250621
π Resources:
MagCache: Fast Video Generation with Magnitude-Aware Cache
NAG: Normalized Attention Guidance
- Project Page β’ Paper β’ GitHub
- Self-Forcing LoRA
DLoRAL: One-Step Video Super-Resolution
- Paper β’ GitHub β’ Demo Video
Physical Art Restoration with AI
- MIT News β’ Nature Paper β’ Nature Video
π° Read the full article: Speed Up Video Generation 2-3x: MagCache, NAG, DLoRAL & AI Art Restoration
Four groundbreaking papers democratizing AI development - from training competitive video models with 256 NPUs to tracking through occlusions, streaming video generation, and climate modeling.
π Resources:
ContentV: Efficient Training of Video Generation Models
- Project Page β’ Paper β’ GitHub
CoTracker3: Tracking Any Point Through Occlusions
- Project Page β’ Paper β’ GitHub
- ComfyUI Node
- See our LEGO DeepDive for CoTracker + ATI workflow
Self-Forcing: Autoregressive Video Diffusion
- Project Page β’ Paper β’ GitHub
CBottle: Climate Foundation Model
- NVIDIA Earth-2 β’ Blog
- Paper β’ GitHub
π° Read the full article: ContentV, CoTracker3, Self-Forcing & CBottle - Democratizing AI Development
Transform a single LEGO photo into a complete animated shot! Join Adrien for an in-depth tutorial combining the latest open-source AI tools to bring our favorite toys to life.
π ComfyUI Workflows & Assets: episodes/20250614
π Resources:
WAN 2.1 + ATI (Any Trajectory Instruction) + VACE + CausVid
CoTracker
SAM2 (Segment Anything 2)
Additional Resources:
π° Read the full article: LEGO Animation DeepDive: WAN + ATI + CoTracker + SAM2 + VACE Complete Workflow
π¬ Master art direction in AI video: normals, bokeh, camera control & trajectories | AInVFX June 6
Learn to art direct Wan 2.1 - Join Adrien for an in-depth ComfyUI tutorial covering four game-changing research papers that enable unprecedented art direction in video diffusion models.
π ComfyUI Workflows & Assets: episodes/20250606
π Resources:
NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors
- Project Page β’ GitHub β’ Paper
- ComfyUI Wrapper
- ComfyUI Workflow β’ Input Video
Any-to-Bokeh: One-Step Video Bokeh via Multi-Plane Image Guided Diffusion
- Project Page β’ GitHub β’ Paper
Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
- Project Page β’ GitHub β’ Paper
- ComfyUI Wrapper β’ Model β’ CausVid LoRA (optional)
- ComfyUI Workflow β’ Input Image β’ 3D Cube
ATI: Any Trajectory Instruction for Controllable Video Generation
- Project Page β’ GitHub β’ Paper
- Model
- ComfyUI Workflow (Start) β’ ComfyUI Workflow (Final) β’ Input Image
π° Read the full article: Art direct Wan 2.1 ComfyUI - ATI, Uni3C, NormalCrafter & Any2Bokeh
Join Adrien as we celebrate 50 years of Industrial Light & Magic, explore Jafar Panahi's inspiring Palme d'Or win at Cannes, and dive into the latest AI developments transforming the VFX industry.
π Resources:
ILM 50th Anniversary
- ILM's Audacious Start β’ Creating the Impossible
- The Dykstraflex β’ John Dykstra Profile
- Rob Bredow TED Talk β’ Original 70s Footage
Cannes 2025
Industry & Research
- Cinesite TechX: Portal β’ Company
- SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding Project β’ Paper β’ GitHub
- Jenga: Training-Free Efficient Video Generation via Dynamic Token Carving Project β’ Paper β’ GitHub
- agenticSeek: Private, Local Manus Alternative GitHub
π° Read the full article: ILM's 50th, Cannes, TechX, SpatialScore, Jenga & AgenticSeek
Follow AInVFX for more AI/VFX updates!
β If you find this helpful, please star this repository!
π‘ About AInVFX News
Led by Adrien (former Head of Effects at WΔtΔ FX), AInVFX bridges the gap between cutting-edge AI research and practical VFX applications.