{"id":"00da52e3-87ea-4bba-a621-49d285c68307","shortId":"mnsMvU","kind":"skill","title":"Stable Diffusion XL LoRA Trainer","tagline":"Fine-tune Stable Diffusion XL models with LoRA adapters using the diffusers library and Kohya-ss training scripts. Manages dataset preparation, training configuration, and checkpoint merging for custom image generation.","description":"# Stable Diffusion XL LoRA Trainer\n\nFine-tune Stable Diffusion XL models with LoRA adapters using the diffusers library and Kohya-ss training scripts. Manages dataset preparation, training configuration, and checkpoint merging for custom image generation.\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- git clone https://github.com/Stability-AI/generative-models.git\n- pip install hatch\n- pip install \"numpy>=1.17\" \"PyWavelets>=1.1.1\" \"opencv-python>=4.1.0.25\"\n- pip install --no-deps invisible-watermark\n\nRequirements and caveats from upstream:\n- python scripts/sampling/simple_video_sample_4d2.py --input_path assets/sv4d_videos/camel.gif --output_folder outputs (after downloading [sv4d2.safetensors](https://huggingface.co/stabilityai/sv4d2.0) from HuggingFace...\n- Run inference: python scripts/sampling/simple_video_sample_4d2.py --input_path <path/to/video>\n- Run inference: python scripts/sampling/simple_video_sample_4d2.py --model_path checkpoints/sv4d2_8views.safetensors --input_path assets/sv4d_videos/chest.gif --output_folder outputs\n\nBasic usage or getting-started notes:\n- To run **SV4D 2.0** on a single input video of 21 frames:\n- **Low VRAM environment** : To run on GPUs with low VRAM, try setting --encoding_t=1 (of frames encoded at a time) and --decoding_t=1 (of frames decoded at a time) or lower video resolution like --img_size=512.\n- The 5x8 model takes 5 frames of input at a time. But the inference scripts for both model take 21-frame video as input by default (same as SV3D and SV4D), we run the model autoregressively until we generate 21 frames.\n\n- Source: https://github.com/Stability-AI/generative-models\n- Extracted from upstream docs: https://raw.githubusercontent.com/Stability-AI/generative-models/HEAD/README.md\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/stable-diffusion-xl-lora-trainer/)","tags":["stable","diffusion","lora","trainer","skills","agentskillexchange","agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex"],"capabilities":["skill","source-agentskillexchange","skill-stable-diffusion-xl-lora-trainer","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/stable-diffusion-xl-lora-trainer","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,905 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:12:37.221Z","embedding":null,"createdAt":"2026-05-18T13:19:37.489Z","updatedAt":"2026-05-18T19:12:37.221Z","lastSeenAt":"2026-05-18T19:12:37.221Z","tsv":"'/skills/stable-diffusion-xl-lora-trainer/)':270 '/stability-ai/generative-models':256 '/stability-ai/generative-models.git':91 '/stability-ai/generative-models/head/readme.md':263 '/stabilityai/sv4d2.0)':131 '1':187,197 '1.1.1':100 '1.17':98 '2.0':164 '21':171,231,251 '4.1.0.25':104 '5':216 '512':211 '5x8':213 'adapt':15,52 'agent':265 'agentskillexchange.com':269 'agentskillexchange.com/skills/stable-diffusion-xl-lora-trainer/)':268 'assets/sv4d_videos/camel.gif':122 'assets/sv4d_videos/chest.gif':150 'autoregress':247 'basic':154 'caveat':115 'checkpoint':32,69 'checkpoints/sv4d2_8views.safetensors':147 'clone':88 'configur':30,67 'custom':35,72 'dataset':27,64 'decod':195,200 'default':237 'dep':109 'diffus':2,10,18,39,47,55 'doc':260 'download':127 'encod':185,190 'environ':86,175 'exchang':267 'extract':257 'fine':7,44 'fine-tun':6,43 'folder':124,152 'frame':172,189,199,217,232,252 'generat':37,74,250 'get':158 'getting-start':157 'git':87 'github.com':90,255 'github.com/stability-ai/generative-models':254 'github.com/stability-ai/generative-models.git':89 'gpus':179 'hatch':94 'huggingfac':133 'huggingface.co':130 'huggingface.co/stabilityai/sv4d2.0)':129 'imag':36,73 'img':209 'infer':135,142,225 'input':120,138,148,168,219,235 'instal':75,79,93,96,106 'invis':111 'invisible-watermark':110 'kohya':22,59 'kohya-ss':21,58 'librari':19,56 'like':208 'lora':4,14,41,51 'low':173,181 'lower':205 'manag':26,63 'match':84 'merg':33,70 'model':12,49,145,214,229,246 'no-dep':107 'note':160 'numpi':97 'opencv':102 'opencv-python':101 'output':123,125,151,153 'path':82,121,139,146,149 'path/to/video':140 'pip':92,95,105 'prepar':28,65 'python':103,118,136,143 'pywavelet':99 'raw.githubusercontent.com':262 'raw.githubusercontent.com/stability-ai/generative-models/head/readme.md':261 'requir':113 'resolut':207 'run':134,141,162,177,244 'script':25,62,226 'scripts/sampling/simple_video_sample_4d2.py':119,137,144 'set':184 'setup':81 'singl':167 'size':210 'skill':266 'skill-stable-diffusion-xl-lora-trainer' 'sourc':253,264 'source-agentskillexchange' 'ss':23,60 'stabl':1,9,38,46 'start':159 'sv3d':240 'sv4d':163,242 'sv4d2.safetensors':128 'take':215,230 'time':193,203,222 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'train':24,29,61,66 'trainer':5,42 'tri':183 'tune':8,45 'upstream':78,117,259 'usag':155 'use':16,53,76 'video':169,206,233 'vram':174,182 'watermark':112 'xl':3,11,40,48","prices":[{"id":"36a7471c-66bd-4b58-8817-9b5c5036e8d2","listingId":"00da52e3-87ea-4bba-a621-49d285c68307","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:19:37.489Z"}],"sources":[{"listingId":"00da52e3-87ea-4bba-a621-49d285c68307","source":"github","sourceId":"agentskillexchange/skills/stable-diffusion-xl-lora-trainer","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/stable-diffusion-xl-lora-trainer","isPrimary":false,"firstSeenAt":"2026-05-18T13:19:37.489Z","lastSeenAt":"2026-05-18T19:12:37.221Z"}],"details":{"listingId":"00da52e3-87ea-4bba-a621-49d285c68307","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"stable-diffusion-xl-lora-trainer","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"e82844108c0ff885662ddf2a5108a794d6ed139c","skill_md_path":"skills/stable-diffusion-xl-lora-trainer/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/stable-diffusion-xl-lora-trainer"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Stable Diffusion XL LoRA Trainer","description":"Fine-tune Stable Diffusion XL models with LoRA adapters using the diffusers library and Kohya-ss training scripts. Manages dataset preparation, training configuration, and checkpoint merging for custom image generation."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/stable-diffusion-xl-lora-trainer"},"updatedAt":"2026-05-18T19:12:37.221Z"}}