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。

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

3,041 subscribers

88,845 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Omer Bar Tal 的头像

Omer Bar Tal3 年前

Our key idea is to define a new generation process, based on an optimization task that binds together multiple diffusion paths. The optimal solution is given in closed-form, and can be found analytically, without a computational overhead. [2/3]

Omer Bar Tal 的头像

Omer Bar Tal3 年前

Visit our project webpage for more details, results, and code 🥳 Arxiv: [3/3]

Omer Bar Tal 的头像

Omer Bar Tal3 年前

MultiDiffusion is now integrated into diffusers 🚀 currently text2panorama is supported, spatial controls (masks/bounding boxes)- soon :) demo: official repo: Thanks @RisingSayak @_akhaliq and @huggingface team!

Hila Chefer 的头像

Hila Chefer3 年前

@YarivLior @lipmanya @talidekel Very cool work! Congrats @omerbartal 🎊

Omer Bar Tal 的头像

Omer Bar Tal3 年前

@YarivLior @lipmanya @talidekel Thanks @hila_chefer :)

Sebastian Bugge Loeschcke 的头像

Sebastian Bugge Loeschcke3 年前

@YarivLior @lipmanya @talidekel Super cool work @omerbartal!

Lucas Beyer (bl16) 的头像

Lucas Beyer (bl16)3 年前

@YarivLior @lipmanya @talidekel Super cool, and nice demo! I think you have a typo in the gif: a tree trunk, not a tree truck, though the latter would also be fun to see =)

Omer Bar Tal 的头像

Omer Bar Tal3 年前

@YarivLior @lipmanya @talidekel Thanks! Ohh definitely a typo, but a cool idea to try ;)

Richard Löwenström 的头像

Richard Löwenström3 年前

@YarivLior @lipmanya @talidekel Nice background trick! I think I've the merging of predictions before though but not so nicely mathematically motivated. I think there's a PR to diffusers upscaling x4 that does something similar for example

Richard Löwenström 的头像

Richard Löwenström3 年前

@YarivLior @lipmanya @talidekel Here's the paper I was thinking about but I may have misunderstood the math 🙏

相关视频

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

👀 Pixel perfect 💎✨ 🖼️ Edify Image from #NVIDIAResearch is a family of diffusion models that supports a wide range of applications, including text-to-image synthesis, 4K upsampling, ControlNets, 360° HDR panorama generation, and finetuning for image customization. 🧵 1/2

👀 Pixel perfect 💎✨ 🖼️ Edify Image from #NVIDIAResearch is a family of diffusion models that supports a wide range of applications, including text-to-image synthesis, 4K upsampling, ControlNets, 360° HDR panorama generation, and finetuning for image customization. 🧵 1/2

NVIDIA AI Developer

14,747 次观看 • 1 年前

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.

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

161,673 次观看 • 2 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

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,113 次观看 • 2 年前

Champ Controllable and Consistent Human Image Animation with 3D Parametric Guidance In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion

Champ Controllable and Consistent Human Image Animation with 3D Parametric Guidance In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion

AK

194,356 次观看 • 2 年前

🤯 OneDiffusion: A versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. ✅ Text to Image ✅ Image to Depth ✅ Image to Segmentation ✅ Image to Pose ✅ FaceID ✅ Image to Multiview How to use & more👇

🤯 OneDiffusion: A versatile, large-scale diffusion model that seamlessly supports bidirectional image synthesis and understanding across diverse tasks. ✅ Text to Image ✅ Image to Depth ✅ Image to Segmentation ✅ Image to Pose ✅ FaceID ✅ Image to Multiview How to use & more👇

Gradio

11,820 次观看 • 1 年前

Canvas-to-Image Compositional Image Generation with Multimodal Controls

Canvas-to-Image Compositional Image Generation with Multimodal Controls

AK

31,268 次观看 • 6 个月前

a year ago, i launched text-behind-image as a 16 y/o went viral with it, grew to 400K+ users today, i'm excited to introduce to you image-behind-image brought to u w/ Cursor + the OG text behind image guy in 1 hr! create image behind image designs easily (link below) 👇

a year ago, i launched text-behind-image as a 16 y/o went viral with it, grew to 400K+ users today, i'm excited to introduce to you image-behind-image brought to u w/ Cursor + the OG text behind image guy in 1 hr! create image behind image designs easily (link below) 👇

Rexan Wong

25,772 次观看 • 10 个月前

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

We’re excited to announce the release and open-source of HunyuanImage 3.0 — the largest and most powerful open-source text-to-image model to date, with over 80 billion total parameters, of which 13 billion are activated per token during inference.The effect is completely comparable to the industry’s flagship closed-source model.🚀🚀🚀 HunyuanImage 3.0 originates from our internally developed native multimodal large language model, with fine-tuning and post-training focused on text-to-image generation. This unique foundation gives the model a powerful set of capabilities: ✅Reason with world knowledge ✅Understand complex, thousand-word prompts ✅Generate precise text within images Different from traditional DiT architecture image generation models, HunyuanImage 3.0’s MoE architecture uses a Transfusion-based approach to deeply couple Diffusion and LLM training for a single, powerful system. Built on Hunyuan-A13B, HunyuanImage 3.0 was trained on a massive dataset: 5 billion image-text pairs, video frames, interleaved image-text data, and 6 trillion tokens of text corpora. This hybrid training across multimodal generation, understanding, and LLM capabilities allows the model to seamlessly integrate multiple tasks. Whether you're an illustrator, designer, or creator, this is built to slash your workflow from hours to minutes. HunyuanImage 3.0 can generate intricate text, detailed comics, expressive emojis, and lively, engaging illustrations for educational content. The current release focuses solely on text-to-image generation and future updates will include image-to-image, image editing, multi-turn interaction, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

412,523 次观看 • 8 个月前

Ovi is out on Hugging Face Twin Backbone Cross-Modal Fusion for Audio-Video Generation Ovi is a veo-3 like, video+audio generation model that simultaneously generates both video and audio content from text or text+image inputs. Video+Audio Generation: Generate synchronized video and audio content simultaneously Flexible Input: Supports text-only or text+image conditioning 5-second Videos: Generates 5-second videos at 24 FPS, area of 720×720, at various aspect ratios (9:16, 16:9, 1:1, etc)

Ovi is out on Hugging Face Twin Backbone Cross-Modal Fusion for Audio-Video Generation Ovi is a veo-3 like, video+audio generation model that simultaneously generates both video and audio content from text or text+image inputs. Video+Audio Generation: Generate synchronized video and audio content simultaneously Flexible Input: Supports text-only or text+image conditioning 5-second Videos: Generates 5-second videos at 24 FPS, area of 720×720, at various aspect ratios (9:16, 16:9, 1:1, etc)

AK

23,082 次观看 • 8 个月前

Phidias A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion discuss: In 3D modeling, designers often use an existing 3D model as a reference to create new ones. This practice has inspired the development of Phidias, a novel generative model that uses diffusion for reference-augmented 3D generation. Given an image, our method leverages a retrieved or user-provided 3D reference model to guide the generation process, thereby enhancing the generation quality, generalization ability, and controllability. Our model integrates three key components: 1) meta-ControlNet that dynamically modulates the conditioning strength, 2) dynamic reference routing that mitigates misalignment between the input image and 3D reference, and 3) self-reference augmentations that enable self-supervised training with a progressive curriculum. Collectively, these designs result in a clear improvement over existing methods. Phidias establishes a unified framework for 3D generation using text, image, and 3D conditions with versatile applications.

Phidias A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion discuss: In 3D modeling, designers often use an existing 3D model as a reference to create new ones. This practice has inspired the development of Phidias, a novel generative model that uses diffusion for reference-augmented 3D generation. Given an image, our method leverages a retrieved or user-provided 3D reference model to guide the generation process, thereby enhancing the generation quality, generalization ability, and controllability. Our model integrates three key components: 1) meta-ControlNet that dynamically modulates the conditioning strength, 2) dynamic reference routing that mitigates misalignment between the input image and 3D reference, and 3) self-reference augmentations that enable self-supervised training with a progressive curriculum. Collectively, these designs result in a clear improvement over existing methods. Phidias establishes a unified framework for 3D generation using text, image, and 3D conditions with versatile applications.

AK

25,120 次观看 • 1 年前

🤯DiffIR2VR-Zero: Zero-shot video restoration to high-resolution using pre-trained image restoration diffusion models. - Framework can handle video denoising and up to 8x super-resolution - outperforms trained models in generalizing across diverse datasets and extreme degradations - Compatible with every 2D restoration model

🤯DiffIR2VR-Zero: Zero-shot video restoration to high-resolution using pre-trained image restoration diffusion models. - Framework can handle video denoising and up to 8x super-resolution - outperforms trained models in generalizing across diverse datasets and extreme degradations - Compatible with every 2D restoration model

Gradio

20,342 次观看 • 1 年前

Flux has arrived to Krea. this new model comes with many styles, image variations, and multiple aspect ratios. free for everyone.

Flux has arrived to Krea. this new model comes with many styles, image variations, and multiple aspect ratios. free for everyone.

Krea

1,184,104 次观看 • 1 年前

New text and image to video generation AI model Open-Sora-Plan-v1.3.0

New text and image to video generation AI model Open-Sora-Plan-v1.3.0

AK

51,823 次观看 • 1 年前

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

Today we’re sharing two new advances in our generative AI research: Emu Video & Emu Edit. Details ➡️ These new models deliver exciting results in high quality, diffusion-based text-to-video generation & controlled image editing w/ text instructions. 🧵

AI at Meta

798,096 次观看 • 2 年前

Object Cutter Create high-quality HD background removal for ANY object in your image with a text prompt or bounding boxes!

Object Cutter Create high-quality HD background removal for ANY object in your image with a text prompt or bounding boxes!

Gradio

135,047 次观看 • 1 年前

FET/ASI Crypto Drops Bombshell Update: Text to Image Generation ASI-1 Mini🔥 ASI-1 Mini is the first model in the ASI:Train family. Today they introduce Text-to-Image Generation, enabling users to create high-quality images from textual descriptions. Fetch.ai Artificial Superintelligence Alliance

FET/ASI Crypto Drops Bombshell Update: Text to Image Generation ASI-1 Mini🔥 ASI-1 Mini is the first model in the ASI:Train family. Today they introduce Text-to-Image Generation, enabling users to create high-quality images from textual descriptions. Fetch.ai Artificial Superintelligence Alliance

cryptoFOXXY

16,613 次观看 • 1 年前

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

AK

40,467 次观看 • 1 年前

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.

The best way to bring the composition from your head into an image → Ideogram V4 + drawing bounding boxes in Comfy. The control here is quite unique. The model uses structured JSON so drawing bounding boxes to get the exact placement works very well. The model only needs 12 steps (turbo), so iterating with different seeds + very impressive text rendering capability leads me to say this is a state of the art open source image model right now. Using the 'Ideogram 4 Prompt Builder' node by Kijai.

rob - comfyui

20,742 次观看 • 3 天前