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).

• 07:29, 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
• 05:48, 11 October 2023 Civitai talk contribs created page Merging (Created page with "See Merge") Tag: Visual edit
• 05:47, 11 October 2023 Civitai talk contribs created page Category:Stable Diffusion Interfaces (Page created) Tag: Visual edit
• 05:47, 11 October 2023 Civitai talk contribs created page Merged (Created page with "See Merge") Tag: Visual edit
• 05:47, 11 October 2023 Civitai talk contribs created page Merge (Created page with "A process by which Checkpoint models are combined (merged) to form new models. Depending on the merge method (see Weighted Sum, Sigmoid) and multiplier, the merged model will retain varying characteristics of its’ constituent models.") Tag: Visual edit
• 05:46, 11 October 2023 Civitai talk contribs created page Metadata (Created page with "Metadata is data that describes data. In the context of Stable Diffusion, metadata is often used to describe the Prompt, Sampler settings, CFG, steps, etc. which are used to define an image, and stored in a .png header.") Tag: Visual edit
• 05:45, 11 October 2023 Civitai talk contribs created page MidJourney (Created page with "A commercial web-based image generation service, similar to DALL-E, or the free, open source, Stable Diffusion.") Tag: Visual edit
• 05:44, 11 October 2023 Civitai talk contribs created page Model (Created page with "See Checkpoint") Tag: Visual edit
• 05:44, 11 October 2023 Civitai talk contribs created page Motion Module (Created page with "Used by AnimateDiff to inject motion into txt2img (or img2img) generations.") Tag: Visual edit
• 05:43, 11 October 2023 Civitai talk contribs created page Inference (Page created) Tag: Visual edit
• 05:43, 11 October 2023 Civitai talk contribs created page Multimodal AI (Created page with "AI that can process multiple types of inputs, including text, images, video or speech.") Tag: Visual edit
• 05:42, 11 October 2023 Civitai talk contribs created page Negative Prompt (Created page with "Keywords which tell a Stable Diffusion prompt what we don’t want to see, in the generated image.") Tag: Visual edit
• 05:42, 11 October 2023 Civitai talk contribs created page Neural Network (Created page with "Mathematical systems that act like a human brain, with layers of artificial “neurons” helping find connections between data.") Tag: Visual edit
• 05:40, 11 October 2023 Civitai talk contribs created page Notebook (Created page with "See Colab") Tag: Visual edit
• 05:39, 11 October 2023 Civitai talk contribs created page NAI (Created page with "See NovelAI") Tag: Visual edit
• 05:38, 11 October 2023 Civitai talk contribs created page NovelAI (Created page with "A paid, subscription based AI-assisted story (text) writing service. Also has a txt2img model, which was leaked and is now incorporated into many Stable Diffusion models.") Tag: Visual edit
• 05:38, 11 October 2023 Civitai talk contribs created page Olivio Sarikas (Created page with "Olivio produces wonderful SD content on YouTube (<nowiki>https://www.youtube.com/@OlivioSarikas</nowiki>) - one of the best SD news YouTubers out there!") Tag: Visual edit