Loading...
Loading...
Found 46 Skills
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
Train custom AI models (LoRA) on fal.ai — personalize image generation for specific people, styles, objects, or video generation. Use when the user requests "Train model", "Train LoRA", "Fine-tune", "Custom model", "Train on my images", "Portrait training".
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Generate images using ModelScope Z-Image models (Z-Image-Turbo, Z-Image, Z-Image-Edit). Use when user asks to generate images, create artwork, or requests image generation functionality. Supports async generation with polling and optional LoRA configurations. IMPORTANT - Model Selection Rule: If the user explicitly mentions "Z-Image-Turbo" in their prompt, use "Tongyi-MAI/Z-Image-Turbo"; if they explicitly mention "Z-Image" (without Turbo), use "Tongyi-MAI/Z-Image"; otherwise, use the default "Tongyi-MAI/Z-Image-Turbo".
Enterprise LLM Fine-Tuning with LoRA, QLoRA, and PEFT techniques
External verl end-to-end validation workflow for Megatron-Bridge model/provider changes. Covers running a small verl Megatron backend job from a Bridge checkout, choosing LoRA/DDP plus optional save/resume and parallelism variants, setting PYTHONPATH so verl imports the local Bridge tree, and reporting pass/fail evidence.
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Prepare datasets and configure LoRA training for character consistency. Covers FLUX (AI-Toolkit, SimpleTuner, FluxGym) and SDXL (Kohya_ss) training with step-by-step guidance. Use when training custom character LoRAs.
LLM fine-tuning with LoRA, QLoRA, and instruction tuning for domain adaptation.
Generate AI images with FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image
Run any model on RunComfy from the command line. The `runcomfy` CLI is one binary, one auth, hundreds of model endpoints — image generation, image edit, video generation, image-to-video, lip-sync, face swap, video edit, inpainting, outpainting, extend, ControlNet, relight, upscale, LoRA training and more. Submit a request, poll for status, download the output. This skill teaches the agent how to install, authenticate, discover model schemas, invoke models, stream / poll / no-wait, script in JSON output mode, and handle errors. Triggers on "runcomfy cli", "install runcomfy", "runcomfy login", "runcomfy run", "runcomfy whoami", "runcomfy api", or any explicit ask to call a RunComfy model from a script or terminal. Sibling skills (ai-image-generation, ai-video-generation, image-edit, video-edit, face-swap, lipsync, image-to-video, image-inpainting, image-outpainting, video-extend, controlnet-pose, relight) all dispatch through this CLI.