#ControlNet

Researchers presented LooseControl, a model that can change AI-generated images by using 3D boxes. You can set up the boxes, and the tool will generate an image based on their positions and sizes. Try the demo: #AI #GenerativeAI #controlnet #technews

#ControlNet #stableDifusion nike 🤤use video loop back and controlnet with canny

Trained an AI model on my face and using #ControlNet #StableDiffusion to guide the facial structure with scribble drawings #ai #experimental #nightmarefuel

Using tools like ControlNet, brands can transcend conventional boundaries of expression and explore new dimensions of creativity. Here’s a cool experiment I did featuring the iconic Nike logo. #ControlNet #Nike

The art of the masters, reimagined. I combined Analog Diffusion with ControlNet to bring Vermeer's 'Girl with a Pearl Earring' to life. The results are stunning. #AIart #NeuralStyle #controlnet

Announcing TemporalNetXL: This is a retrain of TemporalNet1 for Stable Diffusion XL in the diffusers format. The jitter below is as there is no img2img pipeline rn so this is effectively running it at a denoise of 1.0 #stablediffusion #ControlNet

#ControlNet Video UPDATE ✨ — 1. Added specific settings for some control tasks ( canny, hough & normal threshold ) 2. You can now load custom models 🤟 3. Share to Community on private duplicated spaces sends outputs to main community tab — @gradio demo:

Announcing #stablediffusion #ControlNet : TemporalNet 2.0(+ TemporalKit 1.5 with TemporalNet support). TemporalNet 2.0 builds on the original TemporalNet concept, now instead of providing the last frame, you provide the last frame *and* an optical flow map

#ControlNet Video Update ✨ — 1. You can now import GIF 2. All the Control Tasks are available 3. Preprocessor vid output 4. Gif output if you worked from gif 5. All outputs are downloadable 6. Share to community handles more settings Enjoy 🤗 @Gradio :

testing out AI-generated food in mixed reality  #stablediffusion #controlnet #mixedreality #questpro

generative 3D food test #stablediffusion #controlnet

ControlNet experiment where I'm toggling through different styles of contemporary Indian décor, while keeping a consistent scene layout. Loving how ControlNet is putting the artists back in control of AI image generation process. 🧵Thread #ControlNet #StableDiffusion #EbSynth

🧠 AI experiment comparing #ControlNet and #Gen1. Video goes in ➡ Minecraft comes out. Results are wild, and it's only a matter of time till this tech runs at 60fps. Then it'll transform 3D and AR. How soon until we're channel surfing realities layered on top of the world?🧵

#ControlNet canny v. openpose Same settings, strength 2, denoise .7 Canny low threshold 75, high 200, I think low t: 50-75 helps it to find the edges of subjects better than 100 Got better hands Higher res and we'll defined references do help a lot #stablediffusion

#ControlNet is fully integrated with Blender in the latest version of the Dream Textures add-on! Our new node system lets you combine and chain models together to create interesting effects. Here’s a thread of some cool things it can do, starting with poses:

Playing with Stable Diffusion I discovered that it can be used to make realistic images from 3D baby ultrasounds 🤯 #stablediffusion #GenerativeAI #ControlNet #AI

Columbo: Animated - A test. Made with #controlnet - canny edge detection and #AUTOMATIC1111 I think I need to do some comparisons to work out the strengths of different techniques. #aiart #stablediffusion

#ControlNet Video Next Update will let you import animated GIF 🤗 Stay tuned for a detailed tweet about new features, and be aware that the space will be paused tonight during the update process 😉

Mirror Portal 2.0 #warpfusion #stablediffusion #controlnet #aivideo #aiart

Another great example for #ControlNet Video 😁 — It's hard to control the flickering, i recommend to use detailed prompts for better results. The right Control Task is also crucial here 🤗 Share your results 🤠 Follow for updates 🙏 — @Gradio demo link:

Qwen Image 2.1 Update: Speed meets Precision! Achieve 25-step quality in just 8 steps with new acceleration. Now supports 8 ControlNet modes including Pose, Depth, Lineart, and Semantic Segmentation. #QwenImage #ControlNet #AIArt #GenerativeAI