{"id":46040236,"url":"https://github.com/dogbertdev/faststablediffusionxl","last_synced_at":"2026-03-01T06:12:37.989Z","repository":{"id":255264949,"uuid":"848799110","full_name":"dogbertdev/fastStableDiffusionXL","owner":"dogbertdev","description":null,"archived":false,"fork":false,"pushed_at":"2024-08-28T22:27:42.000Z","size":24,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2024-08-28T23:36:03.328Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dogbertdev.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2024-08-28T12:32:40.000Z","updated_at":"2024-08-28T22:27:45.000Z","dependencies_parsed_at":"2024-08-28T23:46:11.539Z","dependency_job_id":null,"html_url":"https://github.com/dogbertdev/fastStableDiffusionXL","commit_stats":null,"previous_names":["dogbertdev/faststablediffusionxl"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/dogbertdev/fastStableDiffusionXL","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dogbertdev%2FfastStableDiffusionXL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dogbertdev%2FfastStableDiffusionXL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dogbertdev%2FfastStableDiffusionXL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dogbertdev%2FfastStableDiffusionXL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dogbertdev","download_url":"https://codeload.github.com/dogbertdev/fastStableDiffusionXL/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dogbertdev%2FfastStableDiffusionXL/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29962005,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-01T05:59:08.471Z","status":"ssl_error","status_checked_at":"2026-03-01T05:58:04.208Z","response_time":124,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":[],"created_at":"2026-03-01T06:12:37.038Z","updated_at":"2026-03-01T06:12:37.967Z","avatar_url":"https://github.com/dogbertdev.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TGATE SDXL Image Generation\n\nThis project implements an image generation pipeline using the Stable Diffusion XL model with TGATE (Text-Guided Attention for Efficient Text-to-Image Generation) and TCD (Temporal Coherence Diffusion) scheduling.\n\n## Features\n\n- Uses Stable Diffusion XL as the base model\n- Implements TGATE for efficient text-to-image generation\n- Utilizes TCD scheduling for improved temporal coherence\n- Supports LoRA (Low-Rank Adaptation) for fine-tuning\n- Configurable image resolution, prompts, and generation parameters\n\n## Requirements\n\n- Python 3.x\n- PyTorch\n- diffusers\n- tgate (custom implementation)\n- CUDA-capable GPU (for optimal performance)\n\n## Setup\n\n1. Clone this repository\n2. Install the required dependencies:\n   ```\n   pip install torch diffusers\n   ```\n3. Place the following files in the same directory as the script:\n   - `aniversePonyXL_v10.safetensors` (base model)\n   - `TCD-SDXL-LoRA.safetensors` (LoRA weights)\n\n## Usage\n\n1. Adjust the prompts, negative prompts, and generation parameters in the script as needed.\n2. Run the script:\n   ```\n   python main.py\n   ```\n3. The generated image will be saved as `image.png` in the same directory.\n\n## Configuration\n\nYou can modify the following parameters in the script:\n\n- `prompt`: The main text prompt for image generation\n- `prompt_2`: Additional text prompt (combined with the main prompt)\n- `negative_prompt`: Text prompt for features to avoid in the generated image\n- `num_inference_steps`: Number of denoising steps\n- `guidance_scale` and `guidance_scale_2`: Guidance scales for the prompts\n- `eta`: Eta value for DDIM sampling\n- `seed`: Random seed for reproducibility\n- `width` and `height`: Output image dimensions\n\n## Advanced Features\n\n- TGATE implementation with configurable gate step, intervals, and warm-up\n- TCD Scheduler for improved temporal coherence\n- LoRA integration for fine-tuned results\n\n## Notes\n\n- The script currently uses CUDA for GPU acceleration. Ensure you have a compatible GPU and CUDA setup.\n- Uncomment the upscaling code if you want to use the 4x upscaling feature (requires additional setup).\n\n\n## Acknowledgements\n\nThis project uses components from various open-source projects, including Stable Diffusion XL, diffusers, and custom implementations of TGATE and TCD.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdogbertdev%2Ffaststablediffusionxl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdogbertdev%2Ffaststablediffusionxl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdogbertdev%2Ffaststablediffusionxl/lists"}