https://github.com/rmurai0610/MASt3R-SLAM
3Dprinting (175) A.I. (733) animation (338) blender (196) colour (229) commercials (49) composition (152) cool (359) design (634) Featured (68) hardware (307) IOS (109) jokes (134) lighting (282) modeling (125) music (185) photogrammetry (177) photography (751) production (1249) python (86) quotes (486) reference (310) software (1330) trailers (296) ves (536) VR (219)
Author: pIXELsHAM.com
-
PixVerse – Prompt, lypsync and extended video generation
https://app.pixverse.ai/onboard
PixVerse now has 3 main features:
text to video➡️ How To Generate Videos With Text Promptsimage to video➡️ How To Animate Your Images And Bring Them To Lifeupscale➡️ How to Upscale Your Video
Enhanced Capabilities
– Improved Prompt Understanding: Achieve more accurate prompt interpretation and stunning video dynamics.
– Supports Various Video Ratios: Choose from 16:9, 9:16, 3:4, 4:3, and 1:1 ratios.
– Upgraded Styles: Style functionality returns with options like Anime, Realistic, Clay, and 3D. It supports both text-to-video and image-to-video stylization.New Features
– Lipsync: The new Lipsync feature enables users to add text or upload audio, and PixVerse will automatically sync the characters’ lip movements in the generated video based on the text or audio.
– Effect: Offers 8 creative effects, including Zombie Transformation, Wizard Hat, Monster Invasion, and other Halloween-themed effects, enabling one-click creativity.
– Extend: Extend the generated video by an additional 5-8 seconds, with control over the content of the extended segment.
-
Alibaba Group Tongyi Lab WanxAI Wan2.1 – open source model
👍 SOTA Performance: Wan2.1 consistently outperforms existing open-source models and state-of-the-art commercial solutions across multiple benchmarks.
🚀 Supports Consumer-grade GPUs: The T2V-1.3B model requires only 8.19 GB VRAM, making it compatible with almost all consumer-grade GPUs. It can generate a 5-second 480P video on an RTX 4090 in about 4 minutes (without optimization techniques like quantization). Its performance is even comparable to some closed-source models.
🎉 Multiple tasks: Wan2.1 excels in Text-to-Video, Image-to-Video, Video Editing, Text-to-Image, and Video-to-Audio, advancing the field of video generation.
🔮 Visual Text Generation: Wan2.1 is the first video model capable of generating both Chinese and English text, featuring robust text generation that enhances its practical applications.
💪 Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information, making it an ideal foundation for video and image generation.
https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files
https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/example%20workflows_Wan2.1
https://huggingface.co/Wan-AI/Wan2.1-T2V-14B
https://huggingface.co/Kijai/WanVideo_comfy/tree/main
-
VES Cinematic Color – Motion-Picture Color Management
This paper presents an introduction to the color pipelines behind modern feature-film visual-effects and animation.
Authored by Jeremy Selan, and reviewed by the members of the VES Technology Committee including Rob Bredow, Dan Candela, Nick Cannon, Paul Debevec, Ray Feeney, Andy Hendrickson, Gautham Krishnamurti, Sam Richards, Jordan Soles, and Sebastian Sylwan.
-
The VFX Reference Platform
The VFX Reference Platform is a set of tool and library versions to be used as a common target platform for building software for the VFX industry. Its purpose is to minimise incompatibilities between different software packages, ease the support burden for integrated pipelines and encourage further adoption of Linux by both studios and software vendors. The Reference Platform is updated annually by a group of software vendors in collaboration with the Visual Effects Society Technology Committee.
Each annual reference platform is designated by the calendar year in which major product releases should be targeting that particular reference.
-
Deep Compositing in Nuke – a walkthrough
Depth Map: A depth map is a representation of the distance or depth information for each pixel in a scene. It is typically a two-dimensional array where each pixel contains a value that represents the distance from the camera to the corresponding point in the scene. The depth values are usually represented in metric units, such as meters. A depth map provides a continuous representation of the scene’s depth information.
For example, in Arnold this is achieved through a Z AOV, this collects depth of the shading points as seen from the camera.
(more…)
https://help.autodesk.com/view/ARNOL/ENU/?guid=arnold_user_guide_ac_output_aovs_ac_aovs_html
https://help.autodesk.com/view/ARNOL/ENU/?guid=arnold_for_3ds_max_ax_aov_tutorials_ax_zdepth_aov_html -
VFX Giant MPC and Parent Company Technicolor Shut Down Amid ‘Severe Financial Challenges
https://variety.com/2025/film/global/technicolor-vfx-mpc-shutter-severe-challenges-1236316354
Shaun Severi, Head of Creative Production at the Mill, claimed in a LinkedIn post that 4,500 had lost their jobs in 24 hours: “The problem wasn’t talent or execution — it was mismanagement at the highest levels…the incompetence at the top was nothing short of disastrous.”
According to Severi, successive company presidents “buried the company under massive debt by acquiring VFX Studios…the second president, after a disastrous merger of the post houses, took us public, artificially inflating the company’s value — only for it to come crashing down when the real numbers were revealed….and the third and final president, who came from a car rental company, had no vision of what she was building, selling or managing.”
-
Moondream Gaze Detection – Open source code
This is convenient for captioning videos, understanding social dynamics, and for specific cases such as sports analytics, or detecting when drivers or operators are distracted.
https://huggingface.co/spaces/moondream/gaze-demo
https://moondream.ai/blog/announcing-gaze-detection
-
X-Dyna – Expressive Dynamic Human Image Animation
https://x-dyna.github.io/xdyna.github.io
A novel zero-shot, diffusion-based pipeline for animating a single human image using facial expressions and body movements derived from a driving video, that generates realistic, context-aware dynamics for both the subject and the surrounding environment.
-
Flex 1 Alpha – a pre-trained base 8 billion parameter rectified flow transformer
https://huggingface.co/ostris/Flex.1-alpha
Flex.1 started as the FLUX.1-schnell-training-adapter to make training LoRAs on FLUX.1-schnell possible.
-
Generative Detail Enhancement for Physically Based Materials
https://arxiv.org/html/2502.13994v1
https://arxiv.org/pdf/2502.13994
A tool for enhancing the detail of physically based materials using an off-the-shelf diffusion model and inverse rendering.
-
Camera Metadata Toolkit (camdkit) for Virtual Production
https://github.com/SMPTE/ris-osvp-metadata-camdkit
Today
camdkitsupports mapping (or importing, if you will) of metadata from five popular digital cinema cameras into a canonical form; it also supports a mapping of the metadata defined in the F4 protocol used by tracking system components from Mo-Sys.
-
OpenTrackIO – free and open-source protocol designed to improve interoperability in Virtual Production
OpenTrackIO defines the schema of JSON samples that contain a wide range of metadata about the device, its transform(s), associated camera and lens. The full schema is given below and can be downloaded here.
-
Martin Gent – Comparing current video AI models
https://www.linkedin.com/posts/martingent_imagineapp-veo2-kling-activity-7298979787962806272-n0Sn
🔹 𝗩𝗲𝗼 2 – After the legendary prompt adherence of Veo 2 T2V, I have to say I2V is a little disappointing, especially when it comes to camera moves. You often get those Sora-like jump-cuts too which can be annoying.
🔹 𝗞𝗹𝗶𝗻𝗴 1.6 Pro – Still the one to beat for I2V, both for image quality and prompt adherence. It’s also a lot cheaper than Veo 2. Generations can be slow, but are usually worth the wait.
🔹 𝗥𝘂𝗻𝘄𝗮𝘆 Gen 3 – Useful for certain shots, but overdue an update. The worst performer here by some margin. Bring on Gen 4!
🔹 𝗟𝘂𝗺𝗮 Ray 2 – I love the energy and inventiveness Ray 2 brings, but those came with some image quality issues. I want to test more with this model though for sure.
-
RigAnything – Template-Free Autoregressive Rigging for Diverse 3D Assets
https://www.liuisabella.com/RigAnything
RigAnything was developed through a collaboration between UC San Diego, Adobe Research, and Hillbot Inc. It addresses one of 3D animation’s most persistent challenges: automatic rigging.
- Template-Free Autoregressive Rigging. A transformer-based model that sequentially generates skeletons without predefined templates, enabling automatic rigging across diverse 3D assets through probabilistic joint prediction and skinning weight assignment.
- Support Arbitrary Input Pose. Generates high-quality skeletons for shapes in any pose through online joint pose augmentation during training, eliminating the common rest-pose requirement of existing methods and enabling broader real-world applications.
- Fast Rigging Speed. Achieves 20x faster performance than existing template-based methods, completing rigging in under 2 seconds per shape.
-
Skywork SkyReels – All-in-one open source AI video creation based on Hynyuan
https://github.com/SkyworkAI/SkyReels-V1
All-in-one AI platform for video creation, including voiceover, lipsync, SFX, and editing. One click turn text to video & image to video. Turns idea into stunning video in minutes. Check Pricing Details. Start For Free. All-In-One Platform.
SkyReels-V1 is purpose-built for AI short video production based on Hynyuan. It achieves cinematic-grade micro-expression performances with 33 nuanced facial expressions and 400+ natural body movements that can be freely combined. The model integrates film-quality lighting aesthetics, generating visually stunning compositions and textures through text-to-video or image-to-video conversion – outperforming all existing open-source models across key metrics.
-
Shanhai based StepFun – Open source Step-Video-T2V
https://huggingface.co/stepfun-ai/stepvideo-t2v
The model generates videos up to 204 frames, using a high-compression Video-VAE (16×16 spatial, 8x temporal). It processes English and Chinese prompts via bilingual text encoders. A 3D full-attention DiT, trained with Flow Matching, denoises latent frames conditioned on text and timesteps. A video-based DPO further reduces artifacts, enhancing realism and smoothness.
COLLECTIONS
| Featured AI
| Design And Composition
| Explore posts
POPULAR SEARCHES
unreal | pipeline | virtual production | free | learn | photoshop | 360 | macro | google | nvidia | resolution | open source | hdri | real-time | photography basics | nuke
FEATURED POSTS
-
copypastecharacter.com – alphabets, special characters and symbols library
-
Web vs Printing or digital RGB vs CMYK
-
59 AI Filmmaking Tools For Your Workflow
-
Black Body color aka the Planckian Locus curve for white point eye perception
-
HDRI Median Cut plugin
-
JavaScript how-to free resources
-
GretagMacbeth Color Checker Numeric Values and Middle Gray
-
Gamma correction
Social Links
DISCLAIMER – Links and images on this website may be protected by the respective owners’ copyright. All data submitted by users through this site shall be treated as freely available to share.