正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Nvidia presents ConsiStory Training-Free Consistent Text-to-Image Generation paper page: enable Stable Diffusion XL (SDXL) to generate consistent subjects across a series of images, without additional training.

AK

502,690 subscribers

161,673 次观看 • 2 年前 •via X (Twitter)

新闻政治科学技术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Furkan Gözükara 的头像

Furkan Gözükara2 年前

We already do this with Dreambooth what is the difference advantage? and still no code :

Cesar Silva 的头像

Cesar Silva2 年前

@Grigomesmo @omisil44

pressed tin 的头像

pressed tin2 年前

things are gonna get wild huh

ari 的头像

ari2 年前

The future of video games is gonna be wild

Vahi Güner 的头像

Vahi Güner2 年前

Important need, character consistency

𝕄𝕚𝕔𝕙𝕒𝕖𝕝 𝕁𝕒𝕞𝕖𝕤 🦅 🇺🇸 的头像

𝕄𝕚𝕔𝕙𝕒𝕖𝕝 𝕁𝕒𝕞𝕖𝕤 🦅 🇺🇸2 年前

🔥

DKRacingFan 的头像

DKRacingFan2 年前

How does it learn without training?

rk⚡fg  的头像

rk⚡fg 2 年前

What would the subject look like if he was...

maru 的头像

maru2 年前

Cool

cardoso 的头像

cardoso2 年前

@artificialguybr

相关视频

✨ 🖼️ Generate images with consistent characters without any fine tuning nor training. Consistory is a training-free approach to maintaining subject consistency between text-to-image generations on pretrained models. #NVIDIAResearch 🎨 Test it here:

✨ 🖼️ Generate images with consistent characters without any fine tuning nor training. Consistory is a training-free approach to maintaining subject consistency between text-to-image generations on pretrained models. #NVIDIAResearch 🎨 Test it here:

NVIDIA AI Developer

11,600 次观看 • 1 年前

Collaborative Score Distillation for Consistent Visual Synthesis paper page: Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented as multiple images (e.g., video), achieving consistency across a set of images is challenging. In this paper, we address this challenge with a novel method, Collaborative Score Distillation (CSD). CSD is based on the Stein Variational Gradient Descent (SVGD). Specifically, we propose to consider multiple samples as "particles" in the SVGD update and combine their score functions to distill generative priors over a set of images synchronously. Thus, CSD facilitates seamless integration of information across 2D images, leading to a consistent visual synthesis across multiple samples. We show the effectiveness of CSD in a variety of tasks, encompassing the visual editing of panorama images, videos, and 3D scenes. Our results underline the competency of CSD as a versatile method for enhancing inter-sample consistency, thereby broadening the applicability of text-to-image diffusion models.

Collaborative Score Distillation for Consistent Visual Synthesis paper page: Generative priors of large-scale text-to-image diffusion models enable a wide range of new generation and editing applications on diverse visual modalities. However, when adapting these priors to complex visual modalities, often represented as multiple images (e.g., video), achieving consistency across a set of images is challenging. In this paper, we address this challenge with a novel method, Collaborative Score Distillation (CSD). CSD is based on the Stein Variational Gradient Descent (SVGD). Specifically, we propose to consider multiple samples as "particles" in the SVGD update and combine their score functions to distill generative priors over a set of images synchronously. Thus, CSD facilitates seamless integration of information across 2D images, leading to a consistent visual synthesis across multiple samples. We show the effectiveness of CSD in a variety of tasks, encompassing the visual editing of panorama images, videos, and 3D scenes. Our results underline the competency of CSD as a versatile method for enhancing inter-sample consistency, thereby broadening the applicability of text-to-image diffusion models.

AK

33,500 次观看 • 2 年前

Open sourcing InScene + InScene Annotate - a pair of LoRAs for steering in-scene image generation w/ QwenEdit. You can use a combination of prompts + annotations to generate consistent images inside a scene. In beta but v. powerful. Model + workflow below, training data soon.

Open sourcing InScene + InScene Annotate - a pair of LoRAs for steering in-scene image generation w/ QwenEdit. You can use a combination of prompts + annotations to generate consistent images inside a scene. In beta but v. powerful. Model + workflow below, training data soon.

POM

71,398 次观看 • 7 个月前

Introducing Stable Diffusion XL beta! Our latest image generation model, now available through our API, excels at photorealism & adds many cool features like enhanced face generation, minimal prompts & legible text. Try out #SDXL in DreamStudio now:

Introducing Stable Diffusion XL beta! Our latest image generation model, now available through our API, excels at photorealism & adds many cool features like enhanced face generation, minimal prompts & legible text. Try out #SDXL in DreamStudio now:

Stability AI

154,805 次观看 • 3 年前

Using the Generative AI Blender add-on with Stable Diffusion XL(+refinement step) to batch generate visual ideas for a screenplay I'm working on: #b3d #vse #aicinema #SDXL

Using the Generative AI Blender add-on with Stable Diffusion XL(+refinement step) to batch generate visual ideas for a screenplay I'm working on: #b3d #vse #aicinema #SDXL

tintwotin

38,665 次观看 • 2 年前

Step into the future of AI image generation with Qwen-Image! From superior text rendering to consistent image editing across multiple languages, it sets a new benchmark! 💡What will you create with Qwen-Image?

Step into the future of AI image generation with Qwen-Image! From superior text rendering to consistent image editing across multiple languages, it sets a new benchmark! 💡What will you create with Qwen-Image?

Alibaba Group

203,475 次观看 • 10 个月前

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

Collaborative Video Diffusion Consistent Multi-video Generation with Camera Control Research on video generation has recently made tremendous progress, enabling high-quality videos to be generated from text prompts or images. Adding control to the video generation

AK

29,262 次观看 • 2 年前

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Introducing SDXL Turbo: A real-time text-to-image generation model. SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one. The code, research paper, and weights for non-commercial use are now available on our website. You can test SDXL Turbo on Stability AI’s image editing platform Clipdrop, with a beta demonstration of the real-time text-to-image generation capabilities. Learn more:

Stability AI

976,258 次观看 • 2 年前

ByteDance just unveiled HuMo, a unified framework for human-centric video generation. With HuMo you can: • Generate videos from text + image • Create audio-synced videos from text + audio • Combine text, image, and audio for maximum control • Preserve consistent subjects across frames • Achieve natural audio-visual synchronization This isn’t just another release , it’s a big step toward fully controllable, coherent, and cinematic AI video.

ByteDance just unveiled HuMo, a unified framework for human-centric video generation. With HuMo you can: • Generate videos from text + image • Create audio-synced videos from text + audio • Combine text, image, and audio for maximum control • Preserve consistent subjects across frames • Achieve natural audio-visual synchronization This isn’t just another release , it’s a big step toward fully controllable, coherent, and cinematic AI video.

DStudioproject

29,408 次观看 • 9 个月前

Google presents MobileDiffusion Subsecond Text-to-Image Generation on Mobile Devices paper page: MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512 × 512 image on mobile devices, establishing a new state of the art.

Google presents MobileDiffusion Subsecond Text-to-Image Generation on Mobile Devices paper page: MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512 × 512 image on mobile devices, establishing a new state of the art.

AK

150,538 次观看 • 2 年前

Stable Diffusion 3.5 from Stability AI is now LIVE on Civitai! Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Generate with SD 3.5 Live on Civitai here👇🏽 All images used to create this video were generated with SD 3.5 by our community 🫶🏽

Stable Diffusion 3.5 from Stability AI is now LIVE on Civitai! Stable Diffusion 3.5 Large is a Multimodal Diffusion Transformer text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency. Generate with SD 3.5 Live on Civitai here👇🏽 All images used to create this video were generated with SD 3.5 by our community 🫶🏽

Civitai

31,235 次观看 • 1 年前

DiffSplat Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation DiffSplat is a generative framework to synthesize 3D Gaussian Splats from text prompts & single-view images in ⚡️ 1~2 seconds. It is fine-tuned directly from a pretrained text-to-image diffusion model.

DiffSplat Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation DiffSplat is a generative framework to synthesize 3D Gaussian Splats from text prompts & single-view images in ⚡️ 1~2 seconds. It is fine-tuned directly from a pretrained text-to-image diffusion model.

AK

38,416 次观看 • 1 年前

Progressive Rendering Distillation released on Hugging Face Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data

Progressive Rendering Distillation released on Hugging Face Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data

AK

12,586 次观看 • 1 年前

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,657 次观看 • 2 年前

3DTopia-XL High-Quality 3D PBR Asset Generation via Primitive Diffusion demo: model: 3DTopia-XL scales high-quality 3D asset generation using Diffusion Transformer (DiT) built upon an expressive and efficient 3D representation, PrimX. The denoising process takes 5 seconds to generate a 3D PBR asset from text/image input which is ready for the graphics pipeline to use.

3DTopia-XL High-Quality 3D PBR Asset Generation via Primitive Diffusion demo: model: 3DTopia-XL scales high-quality 3D asset generation using Diffusion Transformer (DiT) built upon an expressive and efficient 3D representation, PrimX. The denoising process takes 5 seconds to generate a 3D PBR asset from text/image input which is ready for the graphics pipeline to use.

AK

87,086 次观看 • 1 年前

Excited to share "MultiDiffusion"! A controlled image generation framework w/ pre-trained text-to-image diffusion model. * Spatial guidance controls (bounding boxes/masks) * Arbitrary aspect ratios (huge Panoramas!) NO training NO finetuning. [1/3]Lior Yariv Yaron Lipman Tali Dekel

Excited to share "MultiDiffusion"! A controlled image generation framework w/ pre-trained text-to-image diffusion model. * Spatial guidance controls (bounding boxes/masks) * Arbitrary aspect ratios (huge Panoramas!) NO training NO finetuning. [1/3]Lior Yariv Yaron Lipman Tali Dekel

Omer Bar Tal

88,845 次观看 • 3 年前

Bigger. Faster. Stronger. A consistent summer of training and working to build a complete team.

Bigger. Faster. Stronger. A consistent summer of training and working to build a complete team.

LSU Football

24,726 次观看 • 1 年前

"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains" TL;DR: training-free spatio-temporal attention chains generate topology-consistent 4D meshes from video 13× faster while improving temporal correspondence quality

"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains" TL;DR: training-free spatio-temporal attention chains generate topology-consistent 4D meshes from video 13× faster while improving temporal correspondence quality

Alexandre Morgand

13,541 次观看 • 14 天前

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable Diffusion) and retrain to generate multiple consistent views (e.g., a panorama). Project site: Hugging Face demo: Code out in a month.

MVDiffusion: How to take a pre-trained text2image model for a perspective view (e.g., Stable Diffusion) and retrain to generate multiple consistent views (e.g., a panorama). Project site: Hugging Face demo: Code out in a month.

Yasutaka Furukawa

33,418 次观看 • 2 年前