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).

• 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
• 07:29, 11 October 2023 Civitai talk contribs created page Kohya (Page created) Tag: Visual edit
• 07:27, 11 October 2023 Civitai talk contribs created page Gradient Checkpointing (Created page with "Enables intermediate saving of gradients, reduces overall training speed but uses less VRAM. Has no effect on the training results. Category:Training") Tag: Visual edit
• 07:26, 11 October 2023 Civitai talk contribs created page GIT (Created page with "See Generative Image-to-Text Transformer.") Tag: Visual edit
• 07:24, 11 October 2023 Civitai talk contribs created page Generative Image-to-Text Transformer (Created page with "Generative Image-to-Text (GIT), first discussed in [https://arxiv.org/abs/2205.14100 this paper], was trained on 20 million image-text pairs, and further fine-tuned on TextCaps. A robust image-to-text processor.") Tag: Visual edit
• 07:23, 11 October 2023 Civitai talk contribs created page Flip Augmentation (Created page with "Artificially double the number of training images by performing a horizontal flip. If your data is not left-right symmetrical (which will be the case when training humans, subjects), this option should be avoided. Category:Training") Tag: Visual edit
• 07:20, 11 October 2023 Civitai talk contribs created page Color Augmentation (Created page with "Artificially increases the number of training image variations by changing the image hue during learning; supposedly improving model fidelity. When enabled, Cache latents cannot be used due to the training images changing dynamically during training. Category:Training") Tag: Visual edit
• 07:19, 11 October 2023 Civitai talk contribs created page Clip Skip (Created page with "The Text Encoder uses a mechanism called "CLIP", made up of 12 layers (corresponding to the 12 layers of the Stable Diffusion neural network). Clip Skip specified the layer number Xth from the end. Clip Skip of 2 will send the penultimate layer's output vector to the Attention block. Unless the base model you're training against was trained (or Mixed) with Clip Skip 2, you can use 1. SDXL does not benefit from Clip Skip 2.") Tag: Visual edit
• 07:18, 11 October 2023 Civitai talk contribs created page Captioning (Created page with "The process of describing your input training images to help Stable Diffusion understand what it's looking at. Captioning can be done by hand, or via a number of Caption creation tools. Category:Training") Tag: Visual edit
• 07:14, 11 October 2023 Civitai talk contribs created page Cache latents to disk (Created page with "See Cache Latents. Category:Training") Tag: Visual edit
• 07:13, 11 October 2023 Civitai talk contribs created page Cache latents (Created page with "To speed up the LoRA training process, pre-generate the latent representation of the training images in advance, and save into system memory. Category:Training") Tag: Visual edit
• 07:08, 11 October 2023 Civitai talk contribs created page Category:Training (Page created) Tag: Visual edit
• 07:06, 11 October 2023 Civitai talk contribs deleted page Category:LoRA Training (content was: "{{DISPLAYTITLE:Category:Training}} Pages relating to Training LoRA models.", and the only contributor was "Civitai" (talk))
• 07:01, 11 October 2023 Civitai talk contribs created page Category:LoRA Training (Page created) Tag: Visual edit
• 06:55, 11 October 2023 Civitai talk contribs created page Low-Rank Adaptation (Page created) Tag: Visual edit
• 06:54, 11 October 2023 Civitai talk contribs created page Bucket (Page created) Tag: Visual edit
• 06:52, 11 October 2023 Civitai talk contribs created page Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (Page created) Tag: Visual edit
• 06:48, 11 October 2023 Civitai talk contribs created page BLIP (Created page with "Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation (BLIP), created by Salesforce, is a solid, simple image-to-text processor.") Tag: Visual edit
• 06:15, 11 October 2023 Civitai talk contribs created page Prompt (Created page with "Text input to Stable Diffusion describing the particulars of the image you would like output.") Tag: Visual edit
• 06:14, 11 October 2023 Civitai talk contribs created page Lexica (Created page with "Lexica.art, a search engine for stable diffusion art and prompts.") Tag: Visual edit
• 06:13, 11 October 2023 Civitai talk contribs created page LlamaIndex (Created page with "Allows the connection of text data to an LLM via a generated “index”. https://github.com/jerryjliu/llama_index") Tag: Visual edit
• 06:11, 11 October 2023 Civitai talk contribs created page LLM (Created page with "See Large language model") Tag: Visual edit
• 06:10, 11 October 2023 Civitai talk contribs created page Large language model (Created page with "A type of Neural Network that learns to write and converse with users. Trained on billions of pieces of text, LLMs excel at producing coherent sentences and replying to prompts in the correct context. They can perform tasks such as re-writing and summarizing text, chatting about various topics, and performing research.") Tag: Visual edit
• 06:09, 11 October 2023 Civitai talk contribs created page LoCON (Created page with "See LoRA") Tag: Visual edit
• 06:09, 11 October 2023 Civitai talk contribs created page LoHa (Created page with "See LoRA") Tag: Visual edit
• 06:09, 11 October 2023 Civitai talk contribs created page LoKR (Created page with "See LoRA") Tag: Visual edit
• 06:08, 11 October 2023 Civitai talk contribs created page LoRA C3Lier (Created page with "See LoRA") Tag: Visual edit
• 06:06, 11 October 2023 Civitai talk contribs created page Sampler (Created page with "Mathematical functions providing different ways of solving differential equations. Each will produce a slightly (or significantly) different image result from the random latent noise generation.") Tag: Visual edit
• 06:06, 11 October 2023 Civitai talk contribs created page LoRA LierLa (Created page with "See LoRA") Tag: Visual edit
• 06:04, 11 October 2023 Civitai talk contribs created page Epoch (Created page with "The number of times a model training process iterated through a full data set of images. E.g. The 5th Epoc of a Checkpoint model iterated five times through the same data set of images.") Tag: Visual edit
• 06:02, 11 October 2023 Civitai talk contribs created page Emergent Behavior (Created page with "Unintended abilities exhibited by an AI model.") Tag: Visual edit
• 05:58, 11 October 2023 Civitai talk contribs created page Loss (Created page with "A measure of how well an AI model's outputs match the desired outputs.") Tag: Visual edit
• 05:54, 11 October 2023 Civitai talk contribs created page Embedding (Page created) Tag: Visual edit
• 05:53, 11 October 2023 Civitai talk contribs created page Emad (Page created) Tag: Visual edit
• 05:51, 11 October 2023 Civitai talk contribs created page Entropy (Page created) Tag: Visual edit