Topic · AI & LLM Engineering
Best diffusion and image models skills, page 3
Diffusion and image models skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 97 | Adds a generation parameter across MooshieUI's Svelte store, TypeScript types, Rust GenerationParams, and workflow templates. | Mooshieblob1/ | 207 | — | ~417 | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 98 | Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. | artokun/ | 795 | — | ~2.9k | Automated safety check: Notes | MIT | 3 days ago |
| 99 | 99.Image Prompt Write four distinct prompts for AI image models. An agent skill from davidondrej/skills. | davidondrej/ | 4.1k | — | ~659 | Automated safety check: Pass | MIT | yesterday |
| 100 | 100.Custom Nodes The ComfyUI node map — which node lives in which standalone repo vs in-tree under customnodes/, where each is symlinked, and the vendor-sync rule for the vendor/ subsets. | sorryhyun/ | 125 | — | ~470 | Automated safety check: Pass | MIT | today |
| 101 | 101.Vibecomfy Setup Set up VibeComfy for local or remote ComfyUI use. An agent skill from peteromallet/VibeComfy. | peteromallet/ | 150 | — | ~1.5k | Automated safety check: Pass | MIT | 7 days ago |
| 102 | ComfyUI V1 to V3 node migration - converting legacy nodes to the V3 API. | jtydhr88/ | 294 | — | ~3.2k | Automated safety check: Pass | MIT | 2 mo ago |
| 103 | Writes Playwright e2e tests for ComfyUIfrontend. An agent skill from Comfy-Org/ComfyUI_frontend. | Comfy-Org/ | 2.1k | — | ~2.3k | Automated safety check: Pass | GPL-3.0 | today |
| 104 | Write or update Storybook stories for Vue components in ComfyUIfrontend. | Comfy-Org/ | 2.1k | — | ~2.2k | Automated safety check: Pass | GPL-3.0 | today |
| 105 | 105.Pre Commit Check Validates MooshieUI uncommitted changes before commit or PR — build gates, Rust fmt/clippy, conventions, i18n. | Mooshieblob1/ | 207 | — | ~825 | Automated safety check: Pass | AGPL-3.0 | yesterday |
| 106 | ComfyUI node output types - NodeOutput, UI outputs, PreviewImage, PreviewMask, SavedImages, PreviewAudio, PreviewText, PreviewVideo. | jtydhr88/ | 294 | — | ~2.6k | Automated safety check: Pass | MIT | 2 mo ago |
| 107 | A skill your agent uses when reviewing Vitest unit-test diffs in ComfyUIfrontend, especially new mocks, store tests, component tests, or bugfix regression tests. | Comfy-Org/ | 2.1k | — | ~5.1k | Automated safety check: Pass | GPL-3.0 | today |
| 108 | 108.Video Upscale Upscale and restore video in ComfyUI. An agent skill from artokun/comfyui-mcp. | artokun/ | 795 | 1 repo | ~4.3k | Automated safety check: Pass | MIT | 3 days ago |
| 109 | A skill your agent uses when a task involves creating or editing a Scenario workflow graph through MCP: building an app from a brief, adding or rewiring nodes (models, prompts, approval gates… | scenario-labs/ | 913 | — | ~1.9k | Automated safety check: Pass | MIT | 2 days ago |
| 110 | Install Triton + SageAttention to accelerate ComfyUI (the sageattn attentionmode and inductor torch.compile used by WanVideoWrapper / many video graphs). | artokun/ | 795 | — | ~5k | Automated safety check: Pass | MIT | 3 days ago |
| 111 | 111.Add Model Page add, update, or remove a model page entry on the comfy org website. | Comfy-Org/ | 2.1k | — | ~1.5k | Automated safety check: Pass | GPL-3.0 | today |
| 112 | ComfyUI custom node project structure - directory layout, init.py, registration, requirements.txt, publishing, WEBDIRECTORY. | jtydhr88/ | 294 | — | ~2.3k | Automated safety check: Pass | MIT | 2 mo ago |
| 113 | 113.Image Gen Turn a description into an image file with local Stable Diffusion, then iterate on it. | amd/ | 1.6k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 114 | 114.Discover ML Automatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG, embeddings, fine-tuning, LLM, DSPy, HuggingFace, or diffusion models. | rand/ | 181 | 1 repo | ~574 | Automated safety check: Pass | MIT | 7 mo ago |
| 115 | Expert guidance on selecting, fitting, and evaluating drift-diffusion models for two-choice response time data in cognitive science | NeuroAIHub/ | 1.1k | — | ~3k | Automated safety check: Pass | AGPL-3.0 | 6 days ago |
| 116 | 116.Comfyui Core Core ComfyUI knowledge covering workflow format, node types, pipeline patterns, and MCP tool usage | artokun/ | 795 | — | ~3.3k | Automated safety check: Pass | MIT | 3 days ago |
| 117 | Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI | artokun/ | 795 | — | ~2.9k | Automated safety check: Pass | MIT | 3 days ago |
| 118 | Command-line interface for ComfyUI - AI image generation workflow management via ComfyUI REST API. | HKUDS/ | 52k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 16 days ago |
| 119 | 119.Debug Render Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node. | artokun/ | 795 | — | ~1.7k | Automated safety check: Pass | MIT | 3 days ago |
| 120 | 120.Ernie Image Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. | artokun/ | 795 | — | ~4.5k | Automated safety check: Pass | MIT | 3 days ago |
| 121 | 121.Flux Txt2img Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns | artokun/ | 795 | — | ~3k | Automated safety check: Pass | MIT | 3 days ago |
| 122 | 122.Ltx Director Drive the LTX Director (Timeline) node. An agent skill from artokun/comfyui-mcp. | artokun/ | 795 | — | ~1.8k | Automated safety check: Pass | MIT | 3 days ago |
| 123 | 123.Minimax H3 Video Build MiniMax H3 (Hailuo) local video workflows with native T2V/I2V/R2V nodes, Comfy-Org INT8 weights, turbo LoRAs for 8GB VRAM, 15-second stereo-audio clips, and the official MiniMax prompting… | artokun/ | 795 | — | ~3.4k | Automated safety check: Pass | MIT | 3 days ago |
| 124 | Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models | artokun/ | 795 | — | ~4k | Automated safety check: Pass | MIT | 3 days ago |
| 125 | 125.Model Registry Curated download URLs and target directories, organized by family (Flux, WAN, LTX, Qwen, Z-Image, SD15/SDXL), for every model the comfyui-mcp skills reference, covering checkpoints, VAEs, text… | artokun/ | 795 | — | ~2.1k | Automated safety check: Pass | MIT | 3 days ago |
| 126 | ComfyUI prompt engineering knowledge covering CLIP text encoding syntax, weight modifiers, model-specific prompting strategies, and best practices | artokun/ | 795 | — | ~2.9k | Automated safety check: Pass | MIT | 3 days ago |
| 127 | 127.Qwen Txt2img Build Qwen Image 2512 text-to-image workflows with QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants | artokun/ | 795 | — | ~3.3k | Automated safety check: Pass | MIT | 3 days ago |
| 128 | Train a character/identity LoRA locally on FLUX.1-dev via the comfyui-mcp train tools (GPU Docker + ostris ai-toolkit). | artokun/ | 795 | — | ~1.3k | Automated safety check: Pass | MIT | 3 days ago |
| 129 | 129.Troubleshooting Common ComfyUI errors and fixes. An agent skill from artokun/comfyui-mcp. | artokun/ | 795 | — | ~4.5k | Automated safety check: Pass | MIT | 3 days ago |
| 130 | 130.Video Extend Extend / continue a video temporally with Pusa 2.2 in ComfyUI. | artokun/ | 795 | — | ~6.4k | Automated safety check: Pass | MIT | 3 days ago |
| 131 | 131.Wan Multitalk Build WAN MultiTalk audio-driven talking-avatar / lip-sync video workflows. | artokun/ | 795 | — | ~1.3k | Automated safety check: Pass | MIT | 3 days ago |
| 132 | 132.Workflow Layout Lay out and organize a ComfyUI workflow cleanly on the live panel canvas. | artokun/ | 795 | — | ~2.2k | Automated safety check: Pass | MIT | 3 days ago |
| 133 | 133.Z Image Txt2img Build Z-Image txt2img workflows. An agent skill from artokun/comfyui-mcp. | artokun/ | 795 | — | ~2.8k | Automated safety check: Pass | MIT | 3 days ago |
| 134 | 134.Tinker Fine-tune LLMs using the Tinker API. An agent skill from sundial-org/skills. | sundial-org/ | 152 | — | ~1.2k | Automated safety check: Pass | No licence | 2 mo ago |
| 135 | A skill your agent uses when the user mentions Higgsfield Canvas, a node-based or node graph workspace, an infinite board/canvas, chaining generations into a pipeline, or wants to wire prompts →… | OSideMedia/ | 701 | — | ~2.2k | Automated safety check: Pass | MIT | 11 days ago |
| 136 | Generate images via Stable Diffusion (HuggingFace Diffusers, local/API) | taracodlabs/ | 851 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 25 days ago |
| 137 | 137.Stable Diffusion Text-to-image generation, inpainting, and img2img. An agent skill from Luciole-Studio/Misaka-Agent. | Luciole-Studio/ | 139 | 1 repo | ~3.2k | Automated safety check: Pass | MIT | today |
| 138 | 138.Ideogram Ultra Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured… | artokun/ | 795 | — | ~5.6k | Automated safety check: Pass | MIT | 3 days ago |
| 139 | 139.Models Add any Hugging Face image or video model, checkpoint or LoRA to Guaardvark from a URL, list what is installed, and download registry models on request. | guaardvark/ | 255 | — | ~782 | Automated safety check: Pass | MIT | today |
| 140 | 140.Music Video Turn a song into a beat-synced music video with Guaardvark's Director: song analysis, per-cut shot prompts, storyboard keyframes, image-to-video renders, cuts on the beat. | guaardvark/ | 255 | — | ~774 | Automated safety check: Pass | MIT | today |
| 141 | 141.Krea2 Txt2img Build Krea 2 Turbo txt2img workflows with the native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo settings, and Ideogram-style JSON prompting | artokun/ | 795 | — | ~1.9k | Automated safety check: Pass | MIT | 3 days ago |
| 142 | SCAIL-2 in-video character replacement on WAN 2.1. An agent skill from artokun/comfyui-mcp. | artokun/ | 795 | — | ~1.2k | Automated safety check: Pass | MIT | 3 days ago |
| 143 | Rewrite a narrative beat into a rich photoreal visual description suitable for text-to-image models. | UfukNode/ | 181 | — | ~3.1k | Automated safety check: Pass | MIT | 5 mo ago |
| 144 | 144.Comfyui Gateway REST API gateway for ComfyUI servers. An agent skill from majiayu000/claude-skill-registry. | majiayu000/ | 666 | 3 repos | ~3.8k | Automated safety check: Notes | MIT | today |
Explore related skills
Category
More topics in AI & LLM Engineering
- Building AI agents563
- Deep learning415
- Embeddings386
- LLM inference and serving372
- Prompt engineering360
- Retrieval-augmented generation358
- Fine-tuning309
- LLM evaluation308
- Speech recognition and synthesis308
- Structured output and tool calling276
- LLM cost and token optimization259
- LLM API integration255
- Model routing and gateways255
- LLM observability240
- LLM guardrails221
- Computer vision203
- Model hubs and datasets180
- GPU and accelerator computing176
- Natural language processing131
- Reinforcement learning66
- AI interpretability23