{"id":24555750,"url":"https://github.com/ceccon-t/chargen","last_synced_at":"2026-05-17T11:31:13.193Z","repository":{"id":265372923,"uuid":"883473486","full_name":"ceccon-t/Chargen","owner":"ceccon-t","description":"Desktop application to generate character avatars and biographies with local generative AI models.","archived":false,"fork":false,"pushed_at":"2025-01-22T02:12:03.000Z","size":2061,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-22T03:17:49.030Z","etag":null,"topics":["ai","fantasy","image-generation","java","llm","stable-diffusion","text-generation"],"latest_commit_sha":null,"homepage":"","language":"Java","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ceccon-t.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-05T02:53:06.000Z","updated_at":"2025-01-22T02:03:56.000Z","dependencies_parsed_at":"2025-01-22T03:17:54.437Z","dependency_job_id":"090a0685-a2cf-4920-a2e8-34ed18c90ef5","html_url":"https://github.com/ceccon-t/Chargen","commit_stats":null,"previous_names":["ceccon-t/chargen"],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceccon-t%2FChargen","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceccon-t%2FChargen/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceccon-t%2FChargen/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ceccon-t%2FChargen/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ceccon-t","download_url":"https://codeload.github.com/ceccon-t/Chargen/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243905035,"owners_count":20366765,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","fantasy","image-generation","java","llm","stable-diffusion","text-generation"],"created_at":"2025-01-23T04:19:56.490Z","updated_at":"2026-05-17T11:31:13.146Z","avatar_url":"https://github.com/ceccon-t.png","language":"Java","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Chargen\n\n![Build status](https://github.com/ceccon-t/Chargen/actions/workflows/main-workflow.yml/badge.svg \"Build status\")\n\n## Description\n\nDesktop application to generate character avatars and biographies.\n\n![Avatar and biography filled for Human Male Warrior character Gilew Aegold](https://raw.githubusercontent.com/ceccon-t/Chargen/main/images/Chargen_v1-3-0_sc0.png \"Avatar and biography filled for Human Male Warrior character Gilew Aegold\")\n\n## How to use\n\nType in the information about your character on the top left form. After that, click on \"Generate avatar\" button to generate an avatar, and \"Generate bio\" to generate a biography.\n\nIf you like the result, click on the \"Save character\" button at the bottom to save the generated content to disk. A folder will be created with the date and name of the character, containing a JPEG image for the avatar and a plain text file for the biography with all the information of the character.\n\n![Avatar and biography filled for Elf Female Sorcerer character Finduilye Nimrielye](https://raw.githubusercontent.com/ceccon-t/Chargen/main/images/Chargen_v1-3-0_sc1.png \"Avatar and biography filled for Elf Female Sorcerer character Finduilye Nimrielye\")\n\n\n## Dependencies\n\nThe application assumes you have an OpenAI-compatible LLM server listening on port 8080 of your computer and a Stable Diffusion image generation model server listening on port 7860 (both ports can be configured through command line options, check section below). If you have experience configuring and running them, feel free to use your favorite ones - if you do not have experience, the easiest way to get the LLM part running is to use [llamafile](https://github.com/mozilla-Ocho/llamafile), while for the Stable Diffusion model the classic solution is [text-generation-webui](https://github.com/oobabooga/text-generation-webui). Both of these will already start the servers listening on the expected ports by default.\n\nThe application has been developed using as reference models Llama 3.1 8B for text generation, and Stable Diffusion 1.5 for image generation.\n\nDon't like the results you have been getting? Just try different models!\n\n## How to run\n\nThe application is written in Java, so you will need to have the Java runtime installed. Assuming it has already been installed, either download the Jar file from the latest entry in the [Releases](https://github.com/ceccon-t/Chargen/releases) section of this repository or build the project following the instructions below, and execute it.\n\nCommand to run:\n\n`$ java -jar Chargen.jar`\n\nIf building the project with Maven, instead of `Chargen.jar` be sure to use the path to the generated jar, which will be in the `target` directory and have the version as a suffix.\n\n### Run with ollama\n\nIf you are using ollama for the LLM server, you will have to at a minimum pass the name of the model you want to chat with when starting the application by using the `-lm \u003cmodel_name\u003e` option. You will probably also want to use ollama's default port, 11434. Here is an example of how to chat with llama3.1 using ollama (check ollama's documentation for other model options):\n\n`$ java -jar Chargen.jar -lp 11434 -lm llama3.1`\n\n## Command-line options\n\nHere is the list of command-line options available when starting the application:\n\n- `-lp \u003cport_number\u003e`: Set the port where to reach the LLM server, \u003cport_number\u003e must be an integer indicating a port in your machine with a LLM server listening. Defaults to 8080.\n\n- `-sp \u003cport_number\u003e`: Set the port where to reach the Stable Diffusion server, \u003cport_number\u003e must be an integer indicating a port in your machine with a Stable Diffusion server listening. Defaults to 7860.\n\n- `-lm \u003cmodel_name\u003e`: Specify the name of the LLM model to be used, \u003cmodel_name\u003e must be a string. Necessary when using ollama as backend for text generation, has no effect when using llamafile.\n\n- `-lt \u003ctemperature\u003e`: Specify the temperature to be used when generating text, the larger the temperature the more randomness it includes. \u003ctemperature\u003e must be a decimal number, and usually fits in the [0.0-1.0) range. Make sure to use a dot (`.`) and not a comma to separate the parts of the number. Defaults to 0.9.\n\nThese options are independent of each other, and can be combined as desired and in any order. Examples of using some of them can be found in section \"How to run\" of readme.\n\n## How to build the project\n\nThis is a simple Maven project, so the easiest way to build it is running `mvn clean package` in the Chargen folder (assuming Maven is installed - if not, check its site and install from there). A jar file containing everything the application needs to run will be created at `Chargen/target/Chargen-\u003cVERSION\u003e.jar`.\n\n## More info\n\nTo get a short intro to how the code is organized, you can check `architecture.md`.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fceccon-t%2Fchargen","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fceccon-t%2Fchargen","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fceccon-t%2Fchargen/lists"}