Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

✨ 🖼️ 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

111,700 subscribers

11,612 Aufrufe • vor 2 Jahren •via X (Twitter)

Kunst Bildung Wissenschaft & Technologie #NVIDIAResearch

Anya Rossi• Live Now

Private livecam show

2 Kommentare

Profilbild von NVIDIA AI Developer

NVIDIA AI Developervor 2 Jahren

📝 For more details on Consistory check out the #NVIDIAResearch project page: ✨

Profilbild von tom

tomvor 2 Jahren

חמוד

Ähnliche Videos

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

161,717 Aufrufe • vor 2 Jahren

Creativity unleashed 👨‍🎨🎨✨ 👀 Edify3D from #NVIDIAResearch explores a new way to generate text-to-#3D images. 📗 Project page: 📝 Paper: 🔊 sound on

Creativity unleashed 👨‍🎨🎨✨ 👀 Edify3D from #NVIDIAResearch explores a new way to generate text-to-#3D images. 📗 Project page: 📝 Paper: 🔊 sound on

NVIDIA AI Developer

177,497 Aufrufe • vor 1 Jahr

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

📢WorldAgents: 3D worlds only from 2D image models - without any training! We propose an agentic approach with a Director (VLM) to plan the scene, a Generator (Flux or NanoBanana) for new views, and a Verifier (VLM) for selection / 3D consistency. -> High-fidelity 3D worlds from a single text prompt. What's remarkable: our agents find consistent views from 2D image models to obtain 3D-consistent worlds; this shows that image models contain world priors - agents just need to find them! Great work by Ziya Erkoç Angela Dai

Matthias Niessner

19,093 Aufrufe • vor 6 Monaten

Exactly AI Illustrative Training is now on Runware⚙️ - Train a custom model on your brand's visual style - 10–50 images produces a reusable brand-aligned model - Text-to-image + image-to-image with zero style prompting required - Consistent output across campaigns & products

Runware

578,364 Aufrufe • vor 3 Monaten

🚀 Flux from Black Forest Labs is now on RenderNet! Create hyper-realistic, character-consistent images with just one reference image — no LORAs required. Ready to bring your characters to life? Try it with just a few clicks! 🎨✨

🚀 Flux from Black Forest Labs is now on RenderNet! Create hyper-realistic, character-consistent images with just one reference image — no LORAs required. Ready to bring your characters to life? Try it with just a few clicks! 🎨✨

Affogato AI

59,705 Aufrufe • vor 2 Jahren

👀 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 Aufrufe • vor 1 Jahr

Sharing something exciting we've been working on as a Thanksgiving gift: Diffusion Self-Distillation (DSD), which redefines zero-shot customized image generation using FLUX. DSD is like DreamBooth, but zero-shot/training-free. It works across any input subject and desired context—character consistency, item/asset adaptation, scene relighting, and more. It even enables the creation of comics/mangas without any effort in fine-tuning or training a personalized model! 📰 Paper: 🌐 Website: Team effort with Eric Chan, Yunzhi Zhang, Leonidas Guibas, Jiajun Wu, and Gordon Wetzstein.

Sharing something exciting we've been working on as a Thanksgiving gift: Diffusion Self-Distillation (DSD), which redefines zero-shot customized image generation using FLUX. DSD is like DreamBooth, but zero-shot/training-free. It works across any input subject and desired context—character consistency, item/asset adaptation, scene relighting, and more. It even enables the creation of comics/mangas without any effort in fine-tuning or training a personalized model! 📰 Paper: 🌐 Website: Team effort with Eric Chan, Yunzhi Zhang, Leonidas Guibas, Jiajun Wu, and Gordon Wetzstein.

Prime (Shengqu) Cai

60,760 Aufrufe • vor 1 Jahr

T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation paper page: Despite the stunning ability to generate high-quality images by recent text-to-image models, current approaches often struggle to effectively compose objects with different attributes and relationships into a complex and coherent scene. We propose T2I-CompBench, a comprehensive benchmark for open-world compositional text-to-image generation, consisting of 6,000 compositional text prompts from 3 categories (attribute binding, object relationships, and complex compositions) and 6 sub-categories (color binding, shape binding, texture binding, spatial relationships, non-spatial relationships, and complex compositions). We further propose several evaluation metrics specifically designed to evaluate compositional text-to-image generation. We introduce a new approach, Generative mOdel fine-tuning with Reward-driven Sample selection (GORS), to boost the compositional text-to-image generation abilities of pretrained text-to-image models. Extensive experiments and evaluations are conducted to benchmark previous methods on T2I-CompBench, and to validate the effectiveness of our proposed evaluation metrics and GORS approach.

T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation paper page: Despite the stunning ability to generate high-quality images by recent text-to-image models, current approaches often struggle to effectively compose objects with different attributes and relationships into a complex and coherent scene. We propose T2I-CompBench, a comprehensive benchmark for open-world compositional text-to-image generation, consisting of 6,000 compositional text prompts from 3 categories (attribute binding, object relationships, and complex compositions) and 6 sub-categories (color binding, shape binding, texture binding, spatial relationships, non-spatial relationships, and complex compositions). We further propose several evaluation metrics specifically designed to evaluate compositional text-to-image generation. We introduce a new approach, Generative mOdel fine-tuning with Reward-driven Sample selection (GORS), to boost the compositional text-to-image generation abilities of pretrained text-to-image models. Extensive experiments and evaluations are conducted to benchmark previous methods on T2I-CompBench, and to validate the effectiveness of our proposed evaluation metrics and GORS approach.

AK

17,503 Aufrufe • vor 3 Jahren

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

🎉 Meet Krea 2 from Krea, an aesthetic open-source image model ranked #1 text-to-image from an independent lab on Artificial Analysis. Day-0 support is now live in SGLang! Krea 2 ships as two models built to work together: 1️⃣ RAW: undistilled base checkpoint: diverse & malleable, made for fine-tuning, post-training & LoRA 2️⃣ Turbo: 8-step distilled checkpoint: fast, high-quality text-to-image Train LoRAs on RAW, run them on Turbo: base for training, Turbo for fast inference on your own hardware Run it now with SGLang!

LMSYS Org

11,216 Aufrufe • vor 3 Monaten

Wan2.6: Commercial-Grade Image Output Wan2.6-Image is now available. 🖼️ Interleaved Text-and-Image Output：Generate interleaved text-and-image content with logical reasoning capabilities — enabling layered, narrative-driven visual storytelling. 🖼️ Multi-Image Conditioned Generation：Support flexible referencing, combining, and replacement of multiple images, integrating varied visual inspirations to generate novel and compelling results 🖼️ Commercial-Grade ID Preservation：High consistency in characters, styles, and elements for commercial scenarios. 🖼️ Extract creative elements — such as color, style, and composition — from reference images to enable aesthetically driven image generation. 🖼️ Precise Control of Camera Angles and Lighting：Support specifying camera perspective, spatial depth (foreground/background), and lighting details — enabling precise control over spatial composition and atmospheric mood. Try Wan2.6 today.

Wan2.6: Commercial-Grade Image Output Wan2.6-Image is now available. 🖼️ Interleaved Text-and-Image Output：Generate interleaved text-and-image content with logical reasoning capabilities — enabling layered, narrative-driven visual storytelling. 🖼️ Multi-Image Conditioned Generation：Support flexible referencing, combining, and replacement of multiple images, integrating varied visual inspirations to generate novel and compelling results 🖼️ Commercial-Grade ID Preservation：High consistency in characters, styles, and elements for commercial scenarios. 🖼️ Extract creative elements — such as color, style, and composition — from reference images to enable aesthetically driven image generation. 🖼️ Precise Control of Camera Angles and Lighting：Support specifying camera perspective, spatial depth (foreground/background), and lighting details — enabling precise control over spatial composition and atmospheric mood. Try Wan2.6 today.

Wan

33,310 Aufrufe • vor 9 Monaten

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

413,096 Aufrufe • vor 1 Jahr

We’re excited to launch 𝗦𝘆𝗻𝘁𝗵𝗜𝗗 today with GoogleCloud: a digital tool to watermark and identify AI-generated images. 🖼️ It will be available on Imagen, one of Google’s latest text-to-image models. Here’s how it works. 🧵 #GoogleCloudNext

We’re excited to launch 𝗦𝘆𝗻𝘁𝗵𝗜𝗗 today with GoogleCloud: a digital tool to watermark and identify AI-generated images. 🖼️ It will be available on Imagen, one of Google’s latest text-to-image models. Here’s how it works. 🧵 #GoogleCloudNext

Google DeepMind

333,963 Aufrufe • vor 3 Jahren

AI is ready to make full films Seedance 2.0 now can read your entire shot list to generate a full story.. keep characters, props and set design consistent with one image on BytePlus duration and consistency is not a problem anymore here's how with prompts:

AI is ready to make full films Seedance 2.0 now can read your entire shot list to generate a full story.. keep characters, props and set design consistent with one image on BytePlus duration and consistency is not a problem anymore here's how with prompts:

el.cine

416,205 Aufrufe • vor 4 Monaten

How to Train Your Mochi: Introducing LoRA fine-tuning. Customize Mochi on a single GPU with just a few videos. Create any effect or create consistent characters. Make Mochi 1 truly yours.

How to Train Your Mochi: Introducing LoRA fine-tuning. Customize Mochi on a single GPU with just a few videos. Create any effect or create consistent characters. Make Mochi 1 truly yours.

Genmo

114,035 Aufrufe • vor 1 Jahr

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

83,681 Aufrufe • vor 3 Jahren

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,469 Aufrufe • vor 3 Jahren

Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ The 7B & 34B safety tuned models we’ve released can take any combination of text and images as input and produce text outputs using a new early fusion approach. While some LLMs have separate image and text encoders or decoders, Chameleon is one of the first publicly released approaches using a single unified architecture. We’re releasing Chameleon models under a research license to help democratize access to foundational mixed-modal models & further research on early fusion. Approach & training details in the paper ➡️

Last week we released Meta Chameleon: a new mixed-modal research model from Meta FAIR. Get the models ➡️ The 7B & 34B safety tuned models we’ve released can take any combination of text and images as input and produce text outputs using a new early fusion approach. While some LLMs have separate image and text encoders or decoders, Chameleon is one of the first publicly released approaches using a single unified architecture. We’re releasing Chameleon models under a research license to help democratize access to foundational mixed-modal models & further research on early fusion. Approach & training details in the paper ➡️

AI at Meta

54,428 Aufrufe • vor 2 Jahren