Aleksandr

@antmatrosov Do I understand correctly that you extracted 3D from the generated video?

⚡️Hacking Seedance 2.0 for the Image to Gaussian Splat workflow 3DGS scene: superspl.at/scene/1420f92d 15sec video -> Postshot MCMC 1M 90k SSIM 0.94 Video renders: SuperSplat Editor Details below👇 #3dgs #gaussiansplatting #seedance #aivideo #supersplat #playcanvas #lovecraft

4D Gaussian Splatting is mindblowing. How is this level of fidelity and realism able to run so flawlessly on a web browser?

@drawthingsapp Well, finally, it's a very important update! Thank you! You can also add lora -1000/1000 to the settings, or you can manually print a number in any setting by long pressing the number. I hope the translator🙏

🎨 A VERY HANDY canvas feature of Draw Things you might not have noticed yet. 📏 When you adjust the canvas size or accidentally zoom in/out on an image. 🔍 The zoom button now gives you a very quick way to align or fill.

NVIDIA's Kimodo is the release of the week 🔥 Prompt the timeline whatever your want like: "a person walks forward" → "a person starts jumping", hit Generate, and watch a 3D character do it in seconds (700hrs of pro mocap training. Works on human + robot skeletons. Super fast + free to use on HF)

@drawthingsapp And could you reset the settings for this Laura. I downloaded the base model by applying the "z image base 1.0" setting, added Lora and set 2 steps for lora 2-steps, but nothing worked

👇🏻The LoRA link is here: huggingface.co/alibaba-pai/Z-… Note: I have already placed the Draw Things image generation parameters for the two LoRAs in the ALT information of the image above, which you can use as a starting reference for generating images.

🚀 Run Z-Image in Just 2 Steps, Really Impressive！ 🔥 The latest Z-Image-Fun-Lora-Distill-2-Steps-2603 and 4-Steps-2603 LoRAs are TRULY bangers! ✨ Thanks to the addition of a random timesteps strategy, the results this time are absolutely stunning. 💎 While the 2-Steps LoRA delivers solid results, the 4-Steps LoRA can only be described as exceptional.

AI can recreate Chainsaw Man as a cinematic live-action scene. Realistic lighting, smooth motion, and dynamic camera shots make it feel like a real movie.

Seedance 2.0 Omni reference この使い方ガチャ要素なくていいですね 本気でポスプロやる人におすすめ #生成AI

pencil autocomplete #3 realtime model: FLUX.2 [klein] by @bfl_ml via @fal

Apple Vision Pro’s AirDraw app converts 3D drawings into physical objects

Wii Sports in 2026 is about to be crazy

my work on the chainsaw man opening!

A totally new level of pose control in ComfyUI - VNCCS. - full 3D Pose Studio for character posing & lighting, - multi-pose, body generator, pose gallery; - vision-guided QWEN Detailer + camera controls. github.com/AHEKOT/ComfyUI…

Photo Booth 10.0 just dropped

One day, you’ll need the perfect 4DGS video. That’s when we’ll be there for you. Get your lifelike volumetric video done with Gracia’s end-to-end infrastructure, or at least take a moment to see how it works:

Drawing fully interactive physics items in your real life world is incredible I am surprised there hasn’t been more work in this area considering people love both simulation and crafting games (App is AirDraw. Video fully recorded and edited on Headset with native apps)

@drawthingsapp блгодарю

@_trueuser_ blurry, low resolution, pixelated, artifacts, over-smoothing, loss of texture, deformed, watermark, text

🎮 Interesting! I Could Play With This ALL DAY LONG! 🧍 QIE-2511 AnyPose in Draw Things! 🚫 No OpenPose preprocessing Input needed. Just drop a pose reference image into the Draw Things Moodboard, and the character in your original image can mimic any pose. 🤖 Qwen Image Edit 2511 + AnyPose LoRA can achieve the results shown in the examples below. 👇 Click down the post for detailed instructions and parameters.

@drawthingsapp Tell me the whole negative prompt

1️⃣ Arbitrary pose mapping based on a single reference image！ This effect is achieved using the Qwen Image Edit 2511 LoRA, created by lilylilith on Hugging Face. According to the author’s instructions, you need to download and import both LoRA files (Base & Helper) into Draw Things, load both LoRAs, and set the weight of each to 0.7—— 🔗LoRA link：huggingface.co/lilylilith/Any…

Your footage, reimagined. From subtle expressions to bold movements and fully transformed worlds, Dream Lab LA is exploring what’s possible with Ray3 Modify in Dream Machine by @LumaLabsAI

EgoX: Generate immersive first-person video from any third-person clip A novel framework from KAIST AI & Seoul National University that leverages video diffusion models to transform a single exocentric video into a realistic egocentric view. See it in action!