I trained a model on memes from the internet, and made a prompt that tells the Duck to make memes and quack. To my surprise, the Duck began to insert himself into those memes. I cracked up for hours that first night. So far everyone who plays with the Duck a bit finds something
MULTIMODAL AI
-
Eden Art: AI Tools for Creators and Characters
By
–
In 2022, @eden_art_ was born. @xsteenbrugge joined me and we formed a small team that dedicated towards making AI tools for both human creators and agents (or what we called "Characters" in the original app). We made image and video-generating Discord bots as well.
-
Eden.art: AI Agents for Multimedia Content Creation
By
–
Around a year ago, we started building a new app, https://
beta.eden.art which revolves around writing, configuring, and running agents who specialize in making multimedia all the way up to short commercials and reels. The current Abraham account which is autonomously producing -
Better Display Methods for AI Data Visualization
By
–
yeah we a better way to display these. there are subtle differences, bigger might not always be better
-
Using Trained AI Models in Krea.ai Realtime Image Generator
By
–
once the AI model is trained, you can use it in https://t.co/r2gHEVSbZv as follows:
— KREA AI (@krea_ai) 23 janvier 2025
1. open the Style Selector.
2. find your new trained model.
3. select the model and adjust the strength.
4. create! pic.twitter.com/Q4v3IKA6ckonce the AI model is trained, you can use it in https://
krea.ai/apps/image/rea
ltime
… as follows:
1. open the Style Selector.
2. find your new trained model.
3. select the model and adjust the strength.
4. create! -
How to Create Realtime AI Training on Krea
By
–
here's how to create a new Realtime AI training:
— KREA AI (@krea_ai) 23 janvier 2025
1. Head to https://t.co/wqpKvZQ1SE.
2. upload the images that you want to use for the training or re-use images from a previous one.
3. make sure to have "Realtime" active on the settings.
4. train! pic.twitter.com/yjMOAPnDy1here's how to create a new Realtime AI training: 1. Head to http://
krea.ai/train.
2. upload the images that you want to use for the training or re-use images from a previous one.
3. make sure to have "Realtime" active on the settings.
4. train! -
Kimi k1.5: Multimodal Reasoning Model Analysis
By
–
Very good mind path about the kimi k1.5 project, from its contributor, though in Chinese and requiring signing in… 如何评价 Kimi 发布的多模态推理模型 k1.5？ – Flood Sung的回答 – 知乎 https://
zhihu.com/question/10114
790245/answer/84028353434
… -
One-Prompt Consistent Text-to-Image Generation Method
By
–
3/3 Paper "One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation Using a Single Prompt"
-
InterLCM: Latent Consistency Models for Blind Face Restoration
By
–
2/3 Paper "InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restoration"
-
Diffusion Classifier Scores for Personalized Text-to-Image Models
By
–
1/3 For paper “Mining Your Own Secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models” https://
arxiv.org/abs/2410.00700