Agent tasks: Unsloth fine-tuning, ComfyUI face swap, script writing
Melvin Vivas · X post · 2026-10-08 · Open on X
Topics: Fine-tuning & Model Customization, AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator lists tasks his Grok Bots are handling. These include building Colab notebooks to fine-tune small open models (Qwen3.5-4B, Gemma4-E4B) into decision models with Unsloth, face swapping in video with ComfyUI and Minimax H3, and drafting YouTube Shorts scripts. It shows how to hand concrete AI-engineering tasks to agents.
Key points
- Agents can be given whole engineering tasks, such as writing a Colab notebook for fine-tuning.
- Small models around 4B parameters (Qwen3.5-4B, Gemma4-E4B) can be fine-tuned into task-specific 'decision models'.
- Unsloth is the library named for efficient fine-tuning, and it runs in Google Colab.
- ComfyUI plus the Minimax H3 model are used for face swapping in video.
- Agents can also handle content pre-production, such as YouTube Shorts scripts.
Resources mentioned
- Unsloth · tool · unsloth.ai · free
Open-source library for fast, memory-efficient fine-tuning of open LLMs (LoRA/QLoRA) on a single GPU or in Colab.
Also in: 100-Iteration Autonomous Coding Loop with Local Qwen on an RTX 3090 (Melvin Vivas on X · notes), Prompting an Autonomous Agent Loop: Be Specific, Show Visible Progress (Melvin Vivas on X · notes), Running an Overnight 100-Iteration Agent Loop with a Local Qwen Model (Melvin Vivas on X · notes), Train Your Own Decision Model Locally with Unsloth (Melvin Vivas on X · notes) and 36 more - ComfyUI · tool · x.com · free
The official X account for ComfyUI, the node-based tool for generative AI workflows, which announces things like ComfyUI Agent.
Also in: Grok as "Director": Making a Local Anime Clip with ComfyUI on an RTX 3090 (Melvin Vivas on X · notes), FLUX 3 Image Klein: Open-Weights Image Model Now Supported in ComfyUI (Melvin Vivas on X · notes), ComfyUI Templates: Chain Ready-Made Workflows Instead of Building From Scratch (Melvin Vivas on X · notes), Comfy Agent: An AI Agent That Builds ComfyUI Workflows in Comfy Cloud (Melvin Vivas on X · notes) and 32 more - Grok Bot (@bot) on X · tool · x.com · check price
xAI's agent assistant: it does computer tasks, voice calls and email automations, connects to other apps, and can be tagged on X.
Also in: Grok Bot Weekly Update: @bot Tagging on X, Connectors, Voice Memory (Melvin Vivas on X · notes), Troubleshooting 'Bots Aren't Available for This Account' in Grok (Melvin Vivas on X · notes), Tagging @bot on X to send instructions to Grok Bot (Melvin Vivas on X · notes), Grok Bot upgrade: faster agent, X Chat access and new connectors (Melvin Vivas on X · notes) and 7 more - Google Colab · tool · colab.research.google.com · free · recommended by both Bashiri Smith & Melvin Vivas
Free GPU notebooks.
Also in: Run LightOnOCR-3 0.8B and Other Open Models on a Free Colab T4 (Melvin Vivas on X · notes), Try Liquid AI's open d1-3B decision model in Colab (Melvin Vivas on X · notes), Google Colab notebooks for new open models, built by a coding agent (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes) and 27 more - Qwen3.5-4B · tool · huggingface.co · free
Small open-weight Qwen language model with about 4B parameters.
Also in: A day of work done from a phone with Grok Bot agents (Melvin Vivas on X · notes), NuExtract3: Open 4B VLM for OCR and Structured JSON Extraction (Melvin Vivas on X · notes) - Gemma 4 · tool · ai.google.dev · free
Google's family of open-weight models in several sizes, built to run on devices and offline, with multimodal and agentic abilities, and open to fine-tuning.
Also in: Meetily: Open-Source Local AI Meeting Notes App (Melvin Vivas on X · notes), New Gemma Developer Documentation Site (Melvin Vivas on X · notes), A100 80GB GPUs in Google Colab via Google AI Pro plans (Melvin Vivas on X · notes), A day of work done from a phone with Grok Bot agents (Melvin Vivas on X · notes) and 32 more - MiniMax H3 · tool · huggingface.co · free
A MiniMax reference-to-video generation model, run here as an INT8 quantized version for local video head swapping.
Also in: Let an Agent Run Overnight Local Video Generation with ComfyUI (Melvin Vivas on X · notes), Making a 40-Second Anime Episode Locally with ComfyUI on an RTX 3090 (Melvin Vivas on X · notes), Free local anime video generation with Minimax H3 on an RTX 3090 (Melvin Vivas on X · notes), A day of work done from a phone with Grok Bot agents (Melvin Vivas on X · notes) and 4 more
Try this
- Build a Colab notebook that fine-tunes Qwen3.5-4B or Gemma4-E4B with Unsloth into a decision model.
- Build a ComfyUI workflow for face swapping in video using Minimax H3.
- Use an agent to draft YouTube Shorts scripts for pre-production.
More in Fine-tuning & Model Customization
- The Open Env Arena: Agents Design RL Environments, Ranked on a Leaderboard
- Fine-tune and Run Local Models for Free on Google Colab's T4 GPU
- Free Colab notebooks for fine-tuning and running local models
- Train Your Own Decision Model Locally with Unsloth
- Using an ML agent to train an open-source TTS model on your voice
- Run Local Models on a Free GPU with Google Colab (T4)