All public logs

Combined display of all available logs of Civitai Wiki. You can narrow down the view by selecting a log type, the username (case-sensitive), or the affected page (also case-sensitive).

• 16:15, 15 October 2023 Civitai talk contribs created page Temperature (Created page with "When referring to LLMs, '''Temperature''' is a parameter which controls how random a language model's output is. Higher temperature gives the model more leeway and freedom in its responses.") Tag: Visual edit
• 16:12, 15 October 2023 Civitai talk contribs created page Tagging (Created page with "The action of adding descriptive "Tags" or "Captions" to training data images to help the AI model understand what it's seeing during training. See Captioning") Tag: Visual edit
• 16:08, 15 October 2023 Civitai talk contribs created page Civitai CivBot (Created page with "'''CivBot''' is an LLM powered Chatbot, trained on information relating to Civitai, and Generative AI in general. It can answer basic questions about the Civitai platform, provide Stable Diffusion prompts, and provide definitions of complex AI-related terms. Category:Civitai") Tag: Visual edit
• 15:59, 15 October 2023 Civitai talk contribs created page GAN (Created page with "See Generative Adversarial Network") Tag: Visual edit
• 15:53, 15 October 2023 Civitai talk contribs created page Generative Adversarial Network (Created page with "A machine learning model in which two neural networks compete with each other in a goal to generate new data.") Tag: Visual edit
• 06:27, 15 October 2023 Civitai talk contribs created page Greg Rutkowski (Created page with "Traditional artist, vocal opponent of all forms of Generative AI Art. https://www.artstation.com/rutkowski") Tag: Visual edit
• 05:39, 15 October 2023 Civitai talk contribs created page Civitai Bounties (Created page with "Bounties are challenges put forth by our users, each carrying a specific Buzz reward. As such, bounties are a way for the community to collaborate, solve real-world generative AI challenges, and be rewarded for contributing. Category:Civitai") Tag: Visual edit
• 15:34, 13 October 2023 Civitai talk contribs created page Buzz (Created page with "Buzz is the Civitai on-site currency, used to power certain site features. Category:Civitai") Tag: Visual edit
• 20:37, 11 October 2023 Civitai talk contribs created page Prompting (Created page with "See Prompt") Tag: Visual edit
• 17:13, 11 October 2023 Civitai talk contribs created page NLP (Created page with "See Natural Language Processing") Tag: Visual edit
• 17:13, 11 October 2023 Civitai talk contribs created page Natural Language Processing (Created page with "A field of data science that uses machine learning to analyze and "understand" human language. Large Language Models (LLMs) are examples of NLP.") Tag: Visual edit
• 17:11, 11 October 2023 Civitai talk contribs created page Fine-tuning (Created page with "The process of creating a custom model by starting with a general model and using it as the starting point for additional training on custom data. Category:Training") Tag: Visual edit
• 17:08, 11 October 2023 Civitai talk contribs created page AI (Created page with "See Artificial intelligence") Tag: Visual edit
• 17:07, 11 October 2023 Civitai talk contribs created page Artificial intelligence (Created page with "AI is an imprecise term that can have many meanings, to different people. Typically, it refers to the use of ''machine-learning''-based tools in applications that humans interact with directly. It is also a branding term that makes a product that processes data computationally sound complex and futuristic.") Tag: Visual edit
• 17:00, 11 October 2023 Civitai talk contribs created page Machine learning (Created page with "Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn.") Tag: Visual edit
• 16:43, 11 October 2023 Civitai talk contribs created page TencentARC (Created page with "Tencent's Applied Research Center (ARC). TencentARC have produced various models for ControlNet and Image/facial restoration.") Tag: Visual edit
• 16:39, 11 October 2023 Civitai talk contribs created page Category:Face Restoration (Created page with "Pages relating to face restoration methods and models.") Tag: Visual edit
• 16:37, 11 October 2023 Civitai talk contribs created page GFPGAN (Created page with "See Generative Facial Prior Generative Adversarial Network") Tag: Visual edit
• 16:37, 11 October 2023 Civitai talk contribs created page Generative Facial Prior Generative Adversarial Network (Created page with "An algorithm for real-world face restoration, https://github.com/TencentARC/GFPGAN") Tag: Visual edit
• 16:31, 11 October 2023 Civitai talk contribs created page GPU (Created page with "See Graphics processing unit") Tag: Visual edit
• 16:31, 11 October 2023 Civitai talk contribs created page Graphics processing unit (Created page with "A graphics processing unit (GPU) is a specialized electronic circuit initially designed to accelerate computer graphics and image processing. See Nvidia.") Tag: Visual edit
• 15:25, 11 October 2023 Civitai talk contribs created page Category:Stable Diffusion WebUI Plugins & Extensions (Created page with "Plugins and Extensions for Stable Diffusion WebUI and other Interfaces.") Tag: Visual edit
• 08:16, 11 October 2023 Civitai talk contribs created page UNet (Created page with "The UNet is the part of the model architecture which is the "visual memory" of the neural network.") Tag: Visual edit
• 08:14, 11 October 2023 Civitai talk contribs created page WD14 Tagger (Created page with "WD1.4 by SmilingWolf is an image captioning processor with a whole host of variations (including vit-tagger, convnext-tagger, vit-tagger-v2, convnext-tagger-v2, swinv2-tagger-v2). Trained on Danbooru images to various Epochs, with different filtering.") Tag: Visual edit
• 08:13, 11 October 2023 Civitai talk contribs created page Tensorboard (Created page with "A visualization toolkit to track and visualize training metrics like loss and accuracy. Helps determine whether training is going well. Category:Training") Tag: Visual edit
• 08:12, 11 October 2023 Civitai talk contribs created page Text Encoder (Created page with "The Text Encoder (TEnc) controls how the AI interprets text (prompts) while generating, and while training associates tokens (caption words) to blocks in the neural network.") Tag: Visual edit
• 08:08, 11 October 2023 Civitai talk contribs created page Regularization Images (Created page with "Regularization images are images of the same class to the training data - but not the training data. They provide a Dampening effect, and prevent class-drift. Example; if training on images of a female celebrity, regularization images would be images of other women (same class), but not images of the chosen celebrity. Category:Training") Tag: Visual edit
• 07:58, 11 October 2023 Civitai talk contribs created page Optimizer (Created page with "The Optimizer controls how the neural network weights are updated during training. There are various options, and different LoRA guides will suggest different Optimizers and various associated settings. The most commonly used 1.5 Optimizer is AdamW8bit (the default), which uses the least VRAM and has sufficiently good accuracy. Alternatives include DAdaptation, which automatically adjusts the learning rate as trainin...") Tag: Visual edit
• 07:56, 11 October 2023 Civitai talk contribs created page OOM Error (Created page with "See Out of Memory Error.") Tag: Visual edit
• 07:55, 11 October 2023 Civitai talk contribs created page Out of Memory Error (Created page with "Out of Memory (OOM) errors occur when the required VRAM for training exceeds the available VRAM on the GPU. Some LoRA training settings are designed to lower the amount of VRAM used, with a tradeoff in training speed. Category:Training") Tag: Visual edit
• 07:53, 11 October 2023 Civitai talk contribs created page Noise Offset (Created page with "First described by researchers at Crosslabs. A method of introducing true "darkness" (and highlights) into models at the training stage. Note that Noise Offset will increase dampening. A Setting of 0.1 will make a LoRA's colors more vivid. Default is 0. Category:Training") Tag: Visual edit
• 07:52, 11 October 2023 Civitai talk contribs created page Network Rank Dimension (Created page with "Also expressed as Net Dim or Rank. This setting affects the “power” of the model in displaying the concepts trained within. Higher values result in a larger LoRA and more training time, but may capture the element to be trained with better fidelity. Category:Training") Tag: Visual edit
• 07:50, 11 October 2023 Civitai talk contribs created page Network Alpha (Created page with "Closely related to the Network Rank (Dimension), the smaller the Network Alpha value, the larger the LoRA neural net weights. Can be used to Dampen, or "slow down" learning. Alpha of 16 and Network Rank (Dim) of 32 halves the Learning Rate. If Alpha and Network Rank are set to the same value, there will be no effect on Learning Rate. Category:Training") Tag: Visual edit
• 07:48, 11 October 2023 Civitai talk contribs created page Mixed Precision (Created page with "Weight data is originally 32bit units, but we can gain considerable VRAM savings by training with 16bit precision. LoRA can be successfully trained with FP16 (16bit precision). BF16 is a format devised to provide the VRAM savings of FP16 with the accuracy of FP32 (32bit). BF16 may only work on the latest generation GPUs. Category:Training") Tag: Visual edit
• 07:47, 11 October 2023 Civitai talk contribs created page Memory Efficient Attention (Created page with "When enabled, results in greatly lowered VRAM consumption while training, but is slower than Xformers. Default is OFF. Category:Training") Tag: Visual edit
• 07:43, 11 October 2023 Civitai talk contribs created page Learning Rate Scheduler (Created page with "Learning Rate is a parameter of the Optimizer. A Learning Rate Scheduler adjusts the learning rate according to a predefined schedule during the training process. Category:Training") Tag: Visual edit
• 07:42, 11 October 2023 Civitai talk contribs created page Learning Rate (Created page with "The larger the Learning Rate value, the faster the LoRA training, but the more details are missed during training. Low Learning Rates are typically desirable, to retain flexibility in the LoRA. Category:Training") Tag: Visual edit
• 07:40, 11 October 2023 Civitai talk contribs created page Learn Dampening (Created page with "The goal of training is (generally) to fit the most number of Steps in, without Overcooking. Certain settings, by design, or coincidentally, "dampen" learning, allowing us to train more steps before the LoRA appears Overcooked. Some settings which affect Dampening include Network Alpha and Noise Offset.") Tag: Visual edit
• 07:37, 11 October 2023 Civitai talk contribs created page Hugging Face (Created page with "A community/data science platform providing tools to build, train, and deploy machine learning models.") Tag: Visual edit
• 07:36, 11 October 2023 Civitai talk contribs created page Gradio (Created page with "A web-browser based interface framework, specifically for Machine Learning applications. Auto1111 WebUI runs in a Gradio interface.") Tag: Visual edit
• 07:35, 11 October 2023 Civitai talk contribs created page Hallucinations (Created page with "Sometimes LLM models like ChatGPT produce information that sounds plausible but is nonsensical or entirely false. This is called a Hallucination.") Tag: Visual edit
• 07:35, 11 October 2023 Civitai talk contribs created page Inpainting (Created page with "The practice of removing or replacing objects in an image based on a painted mask.") Tag: Visual edit
• 07:33, 11 October 2023 Civitai talk contribs created page LAION (Created page with "See Large-scale Artificial Intelligence Open Network") Tag: Visual edit
• 07:32, 11 October 2023 Civitai talk contribs created page Large-scale Artificial Intelligence Open Network (Created page with "A non-profit organization, providing data sets, tools, and models, for machine learning research.") Tag: Visual edit
• 07:32, 11 October 2023 Civitai talk contribs created page Lanczos (Created page with "An interpolation method used to compute new values for sampled data. In this case, used to upscale images. Named after creator, Cornelius Lanczos.") Tag: Visual edit
• 07:31, 11 October 2023 Civitai talk contribs created page Latent Diffusion (Created page with "A type of diffusion model that contains compressed image representations instead of the actual images. This type of model allows the storage of a large amount of data that can be used by encoders to reconstruct images from textual or image inputs.") Tag: Visual edit
• 07:31, 11 October 2023 Civitai talk contribs created page Latent Mirroring (Created page with "Applies mirroring to the latent images mid-generation to produce anything from subtly balanced compositions to perfect reflections.") Tag: Visual edit
• 07:30, 11 October 2023 Civitai talk contribs created page Latent Space (Created page with "The information-dense space where the diffusion model’s image representation, attention, and transformation are merged and form the initial noise for the diffusion process.") Tag: Visual edit
• 07:30, 11 October 2023 Civitai talk contribs created page LDSR (Created page with "See Latent Diffusion Super Resolution") Tag: Visual edit
• 07:30, 11 October 2023 Civitai talk contribs created page Latent Diffusion Super Resolution (Created page with "A method to increase the dimensions/quality of images.") Tag: Visual edit