mirror of
https://github.com/Comfy-Org/ComfyUI_frontend.git
synced 2026-04-20 14:30:41 +00:00
bbd0a6b201
Migrate workflow_templates/site into the frontend monorepo as apps/hub so the hub can use @comfyorg/design-system and shared packages. Changes to existing files: - pnpm-workspace.yaml: add @astrojs/sitemap, @astrojs/vercel, lucide-vue-next - eslint.config.ts: add hub ignores and i18n/import rule overrides - .oxlintrc.json: add hub scripts to ignore patterns - knip.config.ts: add hub workspace config apps/hub adaptations from source: - Replace local cn() with @comfyorg/tailwind-utils (19 files) - Integrate @comfyorg/design-system/css/base.css in global.css - Make TEMPLATES_DIR configurable via HUB_TEMPLATES_DIR env var - Add HUB_SKIP_SYNC flag for builds without template data - Remove Vite 8-incompatible rollupOptions.output.manualChunks - Fix stylelint violations (modern color notation, number precision) - Gitignore generated content (thumbnails, synced templates, AI cache)
1.8 KiB
1.8 KiB
Samplers & Schedulers
Samplers are the algorithms that iteratively denoise a random latent into a coherent image, while schedulers control the noise schedule — how much noise is removed at each step. Together they determine the image's quality, speed, and visual character. Choosing the right combination is one of the most impactful decisions in any generation workflow.
How It Works in ComfyUI
- Key nodes:
KSampler(main sampling node),KSamplerAdvanced(provides control over start/end steps for multi-pass workflows) - Typical workflow pattern: Load model → connect conditioning → configure sampler/scheduler/steps → sample → decode
Key Settings
- sampler_name: The denoising algorithm. Common choices include
euler(fast, good baseline),euler_ancestral(more creative variation),dpmpp_2m(balanced quality and speed),dpmpp_2m_sde(high quality, slightly slower),dpmpp_3m_sde(very high quality), anduni_pc(fast convergence) - scheduler: Controls the noise reduction curve.
normalis linear,karrasfront-loads noise reduction for better detail,exponentialandsgm_uniform(recommended for SDXL) are also available - steps (1–100): Number of denoising iterations. 20–30 is typical; more steps give diminishing returns. Flux and LCM models need far fewer (4–8 steps)
Tips
euler+normalis the safest starting combination for any modeldpmpp_2m+karrasis a popular choice when you want higher quality with minimal speed cost- Ancestral samplers (
euler_ancestral, any_sdevariant) produce different results each run even with the same seed — useful for exploration, but not for reproducibility - Flux and LCM models converge much faster; using 20+ steps with them wastes time without improving quality