Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

AI can restyle large 3D scenes based on reference images! FPRF is able to stylize NeRF scenes with multiple reference images without additional optimization while preserving multi-view appearance consistency.

Dreaming Tulpa 🥓👑

54,871 subscribers

19,944 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚨 Grok Imagine Reference-to-Video & Extend Video are now live on fal! 🎬 Reference-to-Video: use multiple reference images to generate videos with character/scene consistency 🔁 Extend Video: continue your videos seamlessly

🚨 Grok Imagine Reference-to-Video & Extend Video are now live on fal! 🎬 Reference-to-Video: use multiple reference images to generate videos with character/scene consistency 🔁 Extend Video: continue your videos seamlessly

fal

14,552 views • 3 months ago

The Grok Imagine updates keep accelerating. Reference-to-Video + Video Extend just landed! Live in ComfyUI on Day 0. The generation speed alone makes it worth trying. Reference-to-Video: add up to 7 reference images to generate consistent characters and scenes Video Extend: seamlessly extend any video with smooth, natural motion Workflows and more details about the Grok updates below ⬇️

The Grok Imagine updates keep accelerating. Reference-to-Video + Video Extend just landed! Live in ComfyUI on Day 0. The generation speed alone makes it worth trying. Reference-to-Video: add up to 7 reference images to generate consistent characters and scenes Video Extend: seamlessly extend any video with smooth, natural motion Workflows and more details about the Grok updates below ⬇️

ComfyUI

34,555 views • 3 months ago

Combining ChatGPT Images 2.0 and Seedance 2.0 together. Character sheets are just perfect for using as a reference for your videos. Can really help with consistency. From this character sheet here, I am able to reimagine the same character in different situations. 1. Runner

Combining ChatGPT Images 2.0 and Seedance 2.0 together. Character sheets are just perfect for using as a reference for your videos. Can really help with consistency. From this character sheet here, I am able to reimagine the same character in different situations. 1. Runner

Jerrod Lew

70,250 views • 2 months ago

Seedream 5.0 lite LIVE on Higgsfield at Day-0! 💥 UNLIMITED FOR 7 DAYS on Pro, Ultimate & Creator plans. Seedream 5.0 Lite brings stunning multi-image blending, instant outfit swaps & batch image creation with perfect subject consistency across EVERY frame. Up to 14 reference images with up to 3K resolution on every single output. Powered by ByteDance's most advanced image model yet.

Seedream 5.0 lite LIVE on Higgsfield at Day-0! 💥 UNLIMITED FOR 7 DAYS on Pro, Ultimate & Creator plans. Seedream 5.0 Lite brings stunning multi-image blending, instant outfit swaps & batch image creation with perfect subject consistency across EVERY frame. Up to 14 reference images with up to 3K resolution on every single output. Powered by ByteDance's most advanced image model yet.

Higgsfield AI 🧩

121,310 views • 4 months ago

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

Wonderland: Navigating 3D Scenes from a Single Image Contributions: • First, we introduce a representation for controllable 3D generation by leveraging the generative priors from camera-guided video diffusion models. Unlike image models, video diffusion models are trained on extensive video datasets. This enables them to capture comprehensive spatial relationships within scenes across multiple views and embed a form of "3D awareness" in their latent space, which allows us to maintain 3D consistency in novel view synthesis. • Second, to achieve controllable novel view generation, we empower video models with precise control over specified camera motions. We introduce a novel dual-branch conditioning mechanism that effectively incorporates desired diverse camera trajectories into the video diffusion model. This enables expansion of a single image into a multi-view consistent capture of a 3D scene with precise pose control. • Third, to achieve efficient 3D reconstruction, we directly transform video latents into 3DGS. We propose a novel latent-based large reconstruction model (LaLRM) that lifts video latents to 3D in a feed-forward manner. With this design, during inference, our model directly predicts 3DGS from a single input image, effectively aligning the generation and reconstruction tasks—and bridging image space and 3D space—through the video latent space. Compared with reconstructing scenes from images, the video latent space offers a 256× spatial-temporal reduction while retaining essential and consistent 3D structural details. Such a high degree of compression is crucial, as it allows the LaLRM to handle a wider range of 3D scenes within the reconstruction framework, with the same memory constraints.

MrNeRF

52,801 views • 1 year ago

AI is wild Chatgpt 2.0 images + Seedance 2.0 tried to generate a red carpet AI video using this custom Sydney Sweeney character sheet. the result looks exactly like "we have sydney sweeney at home" 😭 A Simple Prompt used to test - Use the provided character reference for the facial features and body structure. create a 15 second red carpet multi shot walk with elegant designer wear

AI is wild Chatgpt 2.0 images + Seedance 2.0 tried to generate a red carpet AI video using this custom Sydney Sweeney character sheet. the result looks exactly like "we have sydney sweeney at home" 😭 A Simple Prompt used to test - Use the provided character reference for the facial features and body structure. create a 15 second red carpet multi shot walk with elegant designer wear

Dheepan Ratnam

99,600 views • 2 months ago

OpenArt just launched Seedance 2.0 for Teams and Enterprise It delivers the kind of camera control, reference depth, and cinematic storytelling most AI video tools still struggle to offer You can use up to 9 image references, 3 videos, and 3 audio files to build multi-shot scenes with far more control than a normal prompt 10 prompts worth saving:

OpenArt just launched Seedance 2.0 for Teams and Enterprise It delivers the kind of camera control, reference depth, and cinematic storytelling most AI video tools still struggle to offer You can use up to 9 image references, 3 videos, and 3 audio files to build multi-shot scenes with far more control than a normal prompt 10 prompts worth saving:

Amira Zairi

39,913 views • 3 months ago

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Most video tools can generate clips. Very few can maintain identity. That has been the real bottleneck in AI video creation. Kling O1 changes that. For the first time, creators can carry a character, style, and visual language across scenes without constant fixes. You can reference past clips, assets, or images and the output stays consistently on-model. No visual drift. No rework loops. No “this doesn’t look like the last shot” moments. It feels less like prompting a tool and more like working with a creative collaborator that remembers context. The impact is practical, not theoretical: → Faster production cycles → Lower iteration costs → Noticeably higher output quality This is what mature AI tooling looks like. Not louder features. Not bigger claims. Just reliability where it actually matters. Consistency is no longer the problem.

Darshal Jaitwar

141,038 views • 6 months ago

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery Abstract: Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.

MrNeRF

21,346 views • 1 year ago

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!

2023 was the year of AI avatars 2024 was the year of AI photos 2025 was the year of AI videos And I think it's becoming clear now that 2026 will be the year of AI world models Fully interactive explorable 3d worlds generated from one or multiple 2d images or a prompt In turn these 2d images can then be generated by AI too So soon you can generate fully explorable virtual 3d worlds based on your own imagination Next will be figuring out how to make those worlds interactive This is World Labs (unaffiliated, but I like it) As always a lot of big AI model companies are now working on the same thing: 3d world models, only World Labs has a real properly working demo (for now) Very exciting time again!

@levelsio

584,228 views • 10 months ago

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

🚨 Big news: Flux 2 Pro is a new partner model on Adobe Firefly & Photoshop⚡️ What’s special? It’s fast and it’s elite quality. ✅ Better prompt follow-through 🖼️ Up to 4MP images 🌍 Multiple languages support 📌 Multiple reference images ⚙️ Smarter physics Here’s a thread with prompts + where it shines 👇 Bonus news : Unlimited gens until Jan 15 for eligible Firefly Pro/Premium + 7k plans + 5k-credit customers (image models + Firefly Video). This post is sponsored by Adobe through a paid partnership as an Adobe Firefly Ambassador. #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

Umesh

19,281 views • 6 months ago

Character Consistency with Google Veo 3 now in Gemini API! 🤯 Use Images as starting frame to keep character consistency! Here is an python script on how to make consistent viral videos, like you see on TikTok or Youtube shorts: 1. Based on an idea, it generates a series of scene prompts using Gemini 2.5. 2. Generates a Image based on the first scene using Imagen 3 3. For each scene prompt Veo 3 (fast) generates a video clip. 4. Uses Gemini 2.0 image editing to make sure the starting images fits the scenes 5. Combine the individual video clips into a single final video using MoviePy Veo 3 starts at $0.75 / second and Veo 3 at $0.40 / second with audio. ! 📹 🔉 Prompt: “A realistic energy drink commercial for athletes.”

Character Consistency with Google Veo 3 now in Gemini API! 🤯 Use Images as starting frame to keep character consistency! Here is an python script on how to make consistent viral videos, like you see on TikTok or Youtube shorts: 1. Based on an idea, it generates a series of scene prompts using Gemini 2.5. 2. Generates a Image based on the first scene using Imagen 3 3. For each scene prompt Veo 3 (fast) generates a video clip. 4. Uses Gemini 2.0 image editing to make sure the starting images fits the scenes 5. Combine the individual video clips into a single final video using MoviePy Veo 3 starts at $0.75 / second and Veo 3 at $0.40 / second with audio. ! 📹 🔉 Prompt: “A realistic energy drink commercial for athletes.”

Philipp Schmid

15,863 views • 11 months ago

❤️ Runway Aleph 🔥🔈 Testing combining rapid camera movements with preserving core of base video action. example: 'leaving the first frame unchanged, move the camera extremely rapidly to an aerial view above this explosion while keeping the focus on the explosion, then zoom the camera out to reveal the entire complex' Wonder if I can specify the final frame via image reference. Last video is original.

❤️ Runway Aleph 🔥🔈 Testing combining rapid camera movements with preserving core of base video action. example: 'leaving the first frame unchanged, move the camera extremely rapidly to an aerial view above this explosion while keeping the focus on the explosion, then zoom the camera out to reveal the entire complex' Wonder if I can specify the final frame via image reference. Last video is original.

aroha

42,270 views • 11 months ago

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."

Self-Calibrating Gaussian Splatting for Large Field of View Reconstruction Note: Check below for full video. Abstract (cited): "In this paper, we present a self-calibrating framework that jointly optimizes camera parameters, lens distortion, and 3D Gaussian representations, enabling accurate and efficient scene reconstruction. Our technique is particularly effective for high-quality scene reconstruction from large field-of-view (FOV) imagery taken with wide-angle lenses, allowing the scene to be modeled from a smaller number of images. We introduce a novel method for modeling complex lens distortions using a hybrid network that combines invertible residual networks with explicit grids. This design effectively regularizes the optimization process, achieving greater accuracy than conventional camera models. Additionally, we propose a cubemap-based resampling strategy to support large FOV images without sacrificing resolution or introducing distortion artifacts. Our method is compatible with the fast rasterization of Gaussian Splatting, adaptable to a wide variety of camera lens distortions, and demonstrates state-of-the-art performance on both synthetic and real-world datasets."

MrNeRF

17,206 views • 1 year ago

(1/5) Maintain consistency as you execute your creative vision. 🎥 With Ingredients to Video, you can create impactful stories, while maintaining consistent characters across multiple scenes. So, now we can follow the same main characters (a man, his balloon, and a snazzy green and pink car) on an expanding adventure in the Mojave Desert…

(1/5) Maintain consistency as you execute your creative vision. 🎥 With Ingredients to Video, you can create impactful stories, while maintaining consistent characters across multiple scenes. So, now we can follow the same main characters (a man, his balloon, and a snazzy green and pink car) on an expanding adventure in the Mojave Desert…

FlowbyGoogle

35,439 views • 10 months ago

Create a short film like this in just 1 minute with GPT Image 2.0 + Seedance 2.0. GPT Image 2.0 can naturally combine multiple photos into one single image, while Seedance 2.0 can use that image as a reference to automatically separate the scenes, generate a coherent video sequence, and add suitable background music. This workflow greatly improves the overall creative efficiency. When using this method, simply provide the merged image as a reference for Seedance 2.0 and briefly describe each scene with a simple prompt. This can significantly increase the success rate of the final video. All of the above was created on GPT Image Prompt: Seedance Prompt:

Create a short film like this in just 1 minute with GPT Image 2.0 + Seedance 2.0. GPT Image 2.0 can naturally combine multiple photos into one single image, while Seedance 2.0 can use that image as a reference to automatically separate the scenes, generate a coherent video sequence, and add suitable background music. This workflow greatly improves the overall creative efficiency. When using this method, simply provide the merged image as a reference for Seedance 2.0 and briefly describe each scene with a simple prompt. This can significantly increase the success rate of the final video. All of the above was created on GPT Image Prompt: Seedance Prompt:

Midjourney Sref and prompt Library

40,572 views • 2 months ago

So remember that time machine I told you about? I managed to sneek out another video from my visit to the future.. this time I captured video of a 3d artist creating assets for a short commercial. They sculpted the bird in the video with nothing but two controllers which they used to manipulate generative matter in 3d. The AI model changed in realtime and adopted their style of work, both based on the work they did on the scene, and on reference images they gave the system. Seeing the 3d model transform in realtime as they were working on it was incredible. When it started moving and reacted to their instructions, I knew it was time to return to the present :D #art #ai

So remember that time machine I told you about? I managed to sneek out another video from my visit to the future.. this time I captured video of a 3d artist creating assets for a short commercial. They sculpted the bird in the video with nothing but two controllers which they used to manipulate generative matter in 3d. The AI model changed in realtime and adopted their style of work, both based on the work they did on the scene, and on reference images they gave the system. Seeing the 3d model transform in realtime as they were working on it was incredible. When it started moving and reacted to their instructions, I knew it was time to return to the present :D #art #ai

Martin Nebelong

22,044 views • 2 years ago

Dreamina Seedance 2.0 is Officially here! Dreamina Seedance 2.0, ByteDance’s AI-powered creative platform, lets creators easily transform ideas into high-quality videos. You can now edit videos like images, using up to 4 reference modalities (video, image, audio, and text) with precise control over visual effects, camera movements, and more. Why is this revolutionary? - 🔥 One-Prompt Video Editing: Edit videos seamlessly as easily as editing images. - 🎬 Multimodal Creativity: Combine images, video, audio, and text—up to 12 files at once. - 🎥 Remake Viral Content: Create high quality, professional-level videos with intelligent AI. - 🔧 Full Creative Control: Keep consistency in shots, typography, camera flow, and more. This isn’t just another video editing tool, it’s a one-stop AI workspace for all your creative needs. Ready to level up your content? Explore Dreamina Seedance 2.0 and start creating today. 🔗 #dreamina #seedance2 #seedream5 #dreaminatutorial #ai #aitools #aidesign #ecommercedesign #digitalmarketing #startupbusiness

Dreamina Seedance 2.0 is Officially here! Dreamina Seedance 2.0, ByteDance’s AI-powered creative platform, lets creators easily transform ideas into high-quality videos. You can now edit videos like images, using up to 4 reference modalities (video, image, audio, and text) with precise control over visual effects, camera movements, and more. Why is this revolutionary? - 🔥 One-Prompt Video Editing: Edit videos seamlessly as easily as editing images. - 🎬 Multimodal Creativity: Combine images, video, audio, and text—up to 12 files at once. - 🎥 Remake Viral Content: Create high quality, professional-level videos with intelligent AI. - 🔧 Full Creative Control: Keep consistency in shots, typography, camera flow, and more. This isn’t just another video editing tool, it’s a one-stop AI workspace for all your creative needs. Ready to level up your content? Explore Dreamina Seedance 2.0 and start creating today. 🔗 #dreamina #seedance2 #seedream5 #dreaminatutorial #ai #aitools #aidesign #ecommercedesign #digitalmarketing #startupbusiness

GitHub Projects Community

18,440 views • 3 months ago

I vibe coded a visual PDF search app with ColQwen2. This is how it works: - Store PDF files as images in a Weaviate AI Database vector database - Embed images and text with a multimodal late-interaction model (ColQwen2) - Generate token-wise (and summed) similarity maps to highlight image patches with high similarity Now I need to refactor the messy vibe-coded project. In the meantime, you can check out the Notebook this demo is based on to try it out yourself:

I vibe coded a visual PDF search app with ColQwen2. This is how it works: - Store PDF files as images in a Weaviate AI Database vector database - Embed images and text with a multimodal late-interaction model (ColQwen2) - Generate token-wise (and summed) similarity maps to highlight image patches with high similarity Now I need to refactor the messy vibe-coded project. In the meantime, you can check out the Notebook this demo is based on to try it out yourself:

Leonie

34,494 views • 10 months ago