domain-generative
Skill8 starsChanged 4 months agoMITView on GitHub
Use for generative modeling of images and audio: text-to-image, image editing or image-to-image, unconditional image generation, inpainting, super-resolution, style transfer, and audio or music generation, including fine-tuning or personalizing a base model. Picks diffusion vs GAN, the right adaptation method, and generation-specific evaluation. For text generation use domain-nlp-llm instead. Triggers on 'generate images', 'text to image', 'diffusion', 'stable diffusion', 'GAN', 'image editing', 'inpainting', 'super resolution', 'synthesize', 'DreamBooth', 'LoRA image'.
In this repository22 other files it gives its agents.
- accuracy-improvement-loopSkill
- data-rigor-and-leakageSkill
- dataset-profilingSkill
- deployment-explainabilitySkill
- domain-3dSkill
- domain-anomaly-detectionSkill
- domain-audio-speechSkill
- domain-computer-visionSkill
- domain-graphSkill
- domain-medical-imagingSkill
- domain-multimodalSkill
- domain-nlp-llmSkill
- domain-recommenderSkill
- domain-reinforcement-learningSkill
- domain-tabularSkill
- domain-time-seriesSkill
- domain-videoSkill
- literature-reviewSkill
- ml-research-methodologySkill
- notebook-deliverySkill
- rigorous-evaluationSkill
- training-optimizationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Prefer fine-tuning a strong pretrained base over training from scratch.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Generative Models - Method Selection
Prefer fine-tuning a strong pretrained base over training from scratch. Use classifier-free guidance for text alignment.
Decision table
| Sub-task | Recommended | Notes |
| Text-to-image or general image generation | latent diffusion (Stable Diffusion family, SDXL) | diffusion now beats GANs on quality and diversity. |
| Personalize or customize on a few images | LoRA, DreamBooth, or textual inversion on a diffusion base | parameter-efficient, small data. |
| Fast or real-time, or paired image-to-image | GAN (pix2pix, StyleGAN) or a distilled diffusion model | GANs are faster at inference. |
| Inpainting or super-resolution | diffusion inpainting, Real-ESRGAN | |
| Audio or music generation | diffusion, or a transformer LM over audio tokens |
Cross-cutting practice
- Metrics: FID and KID (fidelity and diversity versus real data), CLIP score (text-image alignment), IS. For personalization, measure subject fidelity and prompt fidelity separately. Automatic metrics are weak proxies, so human evaluation remains essential. Do not judge on a single number.
- Caveats: generated data can carry artifacts, so training a downstream model on synthetic data can hurt. Watch for training-data memorization, plus licensing and safety.
- Explainability: cross-attention maps (which words drove which region) and guidance-scale sweeps.
- Recent bases (2024): SD3 and FLUX text-to-image, plus consistency and distilled models for fast few-step sampling.
- Improve results: use
accuracy-improvement-loop; evaluate withrigorous-evaluation(generation metrics plus human review).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.