UNPKG

comfyui-mcp

Version:

Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),

509 lines (485 loc) • 18.7 kB
{ "$schema": "model-settings.schema.json", "_version": "0.2.0", "_description": "Community-maintained best settings for ComfyUI models. Merge order: defaults (this file) → user overrides (model-settings.user.json). PRs welcome!", "_updated": "2026-02-16", "_merge_strategy": "deep_merge_user_wins", "model_families": { "qwen_image": { "display_name": "Qwen Image (Base Architecture)", "architecture": "qwen_image", "clip_type": "qwen_image", "vae": "qwen_image_vae.safetensors", "prompt_style": "natural_language", "prompt_notes": "Use natural language, 1-3 sentences. Put text to render in quotes. 'photograph' > 'photorealistic'. Negative prompts: use NLP-style descriptions, not keyword spam.", "resolutions": { "_note": "Qwen Image operates at ~1.6 megapixels natively", "square": [1328, 1328], "portrait_3_4": [1104, 1472], "portrait_9_16": [928, 1664], "portrait_2_3": [1056, 1584], "landscape_4_3": [1472, 1104], "landscape_16_9": [1664, 928], "landscape_3_2": [1584, 1056], "ultrawide_portrait": [1536, 2048] }, "presets": { "lightning_4step": { "description": "Fast 4-step with LightX2V lightning LoRA. Good general-purpose.", "steps": 4, "cfg": 1.0, "sampler": "euler", "scheduler": "simple", "denoise": 1.0, "auraflow_shift": 3.1, "lora": { "name": "Qwen-Image-Lightning-4steps-V1.0.safetensors", "strength": 1.0 }, "notes": "For 2511 edit models, use 2511-specific lightning LoRA." }, "lightning_4step_2511_edit": { "description": "Fast 4-step specifically for 2511 edit model.", "steps": 4, "cfg": 1.0, "sampler": "euler", "scheduler": "simple", "denoise": 1.0, "lora": { "name": "Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors", "strength": 1.0 }, "notes": "Cannot combine with distilled model variant." }, "lightning_8step": { "description": "Higher quality 8-step lightning. Better detail than 4-step.", "steps": 8, "cfg": 1.0, "sampler": "euler", "scheduler": "simple", "denoise": 1.0, "auraflow_shift": 3.1, "lora": { "name": "Qwen-Image-Lightning-8steps-V1.0.safetensors", "strength": 1.0 } }, "lightning_8step_character": { "description": "8-step lightning tuned for detailed character/portrait work.", "steps": 8, "cfg": 2.5, "sampler": "euler", "scheduler": "simple", "denoise": 1.0, "auraflow_shift": 3.1, "lora": { "name": "Qwen-Image-Lightning-8steps-V1.0.safetensors", "strength": 1.0 }, "notes": "CFG 2.5 gives better prompt adherence for character details (Imageized author examples)." }, "standard": { "description": "Official full-quality settings from ComfyUI template.", "steps": 50, "cfg": 4.0, "sampler": "euler", "scheduler": "simple", "denoise": 1.0, "auraflow_shift": 3.1, "notes": "Official ComfyUI workflow template values. 30-50 steps work well." }, "standard_golden": { "description": "Community-tested 'golden configuration' for best quality.", "steps": 50, "cfg": 4.5, "sampler": "euler", "scheduler": "simple", "denoise": 1.0, "auraflow_shift": 3.1, "notes": "Community consensus: CFG 4.5 + 50 steps for peak quality." }, "standard_character_composition": { "description": "Optimized for multi-character scenes and complex compositions.", "steps": 30, "cfg": 4.0, "sampler": "euler_ancestral", "scheduler": "beta", "denoise": 1.0, "auraflow_shift": 3.1, "notes": "euler_ancestral + beta helps with character variety and scene coherence." } } }, "qwen_image_2512": { "display_name": "Qwen Image 2512 (December 2025)", "inherits": "qwen_image", "unet": "qwen_image_2512_fp8_e4m3fn.safetensors", "clip": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "vae": "qwen_image_vae.safetensors", "notes": "Latest official Qwen Image model. fp8 for 24GB VRAM. Inherits all qwen_image presets." }, "qwen_image_2511_edit": { "display_name": "Qwen Image Edit 2511 (November 2025)", "inherits": "qwen_image", "unet": "qwen_image_edit_2511_bf16.safetensors", "clip": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "vae": "qwen_image_vae.safetensors", "notes": "Optimized for image editing. bf16 precision. Use 2511-specific lightning LoRA.", "presets": { "edit_standard": { "description": "Full quality img2img editing.", "steps": 40, "cfg": 4.0, "sampler": "euler", "scheduler": "simple", "denoise": 0.75, "notes": "Denoise 0.5-0.8: lower = closer to input. Negative conditioning should be zeroed." } } }, "qwen_finetuned": { "display_name": "Qwen Image Fine-tuned Models", "architecture": "qwen_image", "models": { "qwenUltimateRealism_v11": { "display_name": "Qwen Ultimate Realism v1.1", "author": "Imageized", "source": "https://civitai.com/models/2027494", "unet_path": "Qwen/imageized/qwenUltimateRealism_v11.safetensors", "clip": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "vae": "qwen_image_vae.safetensors", "focus": "Product photography, hyper-realistic, e-commerce", "presets": { "author_quality": { "description": "Author's best quality settings.", "steps": 30, "cfg": 7.5, "sampler": "euler", "scheduler": "simple", "denoise": 1.0, "notes": "Steps 20-40, CFG 5-10 (sweet spot 7-8)." }, "author_fast": { "steps": 4, "cfg": 1.0, "sampler": "euler", "scheduler": "simple", "lora": { "name": "Qwen-Image-Lightning-4steps-V1.0.safetensors", "strength": 1.01 }, "notes": "Author uses strength 1.01 specifically." } } }, "copaxTimeless_qwenUltraRealistic": { "display_name": "CopaxTimeless Qwen Ultra Realistic", "author": "Copax", "source": "https://civitai.com/models/copaxTimeless", "unet_path": "Qwen/realistic/copaxTimeless_qwenUltraRealistic.safetensors", "clip": "qwen_2.5_vl_7b_fp8_scaled.safetensors", "vae": "qwen_image_vae.safetensors", "focus": "Ultra-realistic portraits and scenes", "presets": { "author_recommended": { "steps": 30, "cfg": 4.0, "sampler": "res_multistep", "scheduler": "sgm_uniform", "denoise": 1.0, "auraflow_shift": 3.1, "notes": "Consistently uses res_multistep + sgm_uniform. Steps 20/30/50 all work." } }, "resolutions": [ [1152, 1536], [992, 1776], [928, 1984], [1536, 2048] ] }, "redcraftRedzimage_DX1": { "display_name": "RedCraft Redzimage DX1", "source": "https://civitai.com/models/958009", "unet_path": "redcraftRedzimageUpdatedJAN30_redzibDX1.safetensors", "loader": "CheckpointLoaderSimple", "focus": "Realistic generation (combined checkpoint)", "presets": { "distilled_fast": { "steps": 10, "cfg": 1.0, "sampler": "euler", "scheduler": "simple" }, "standard": { "steps": 30, "cfg": 4.0, "sampler": "euler", "scheduler": "simple" } }, "notes": "Combined checkpoint (UNET+CLIP+VAE). Use CheckpointLoaderSimple, not separate loaders." } } }, "z_image": { "display_name": "Z-Image Family", "architecture": "z_image", "notes": "Must use Qwen tokenizer, not standard CLIP nodes.", "models": { "z_image_turbo": { "display_name": "Z-Image Turbo", "unet": "z_image_turbo_bf16.safetensors", "clip": "qwen_3_4b.safetensors", "vae": "z-image-ae.safetensors", "clip_type": "qwen_image", "presets": { "author_recommended": { "steps": 14, "cfg": 1.0, "sampler": "res_2s", "scheduler": "simple", "notes": "From CopaxTimeless author. Distilled CFG 1." }, "beauty_fashion": { "steps": 10, "cfg": 1.0, "sampler": "euler_ancestral", "scheduler": "beta", "notes": "Smooth skin, ideal for beauty/fashion (560-image test)." }, "sharpest": { "steps": 10, "cfg": 1.0, "sampler": "dpmpp_sde", "scheduler": "beta", "notes": "Sharpest, most natural results from community testing." } }, "negative_prompt_template": "over-smooth skin, plastic skin, doll face, anime, CGI, waxy texture, blurry face, fake pores, exaggerated makeup, over-sharpening, unrealistic symmetry, flat lighting, low detail skin, extra fingers, distorted anatomy" } } }, "sdxl": { "display_name": "SDXL 1.0", "architecture": "sdxl", "clip_type": "sdxl", "prompt_style": "tags_and_natural", "presets": { "realistic_photo": { "description": "Gold standard for SDXL photorealism.", "steps": 25, "cfg": 5.0, "sampler": "dpmpp_2m", "scheduler": "karras", "notes": "DPM++ 2M Karras. CFG 5-7. AVOID Euler for SDXL (causes washed-out images)." }, "realistic_creative": { "description": "More diverse realistic results.", "steps": 30, "cfg": 6.0, "sampler": "dpmpp_2m_sde", "scheduler": "karras", "notes": "DPM++ 2M SDE Karras for more creative variation." }, "realistic_best": { "description": "Highest quality realistic (slow).", "steps": 35, "cfg": 6.0, "sampler": "heun", "scheduler": "normal", "notes": "Heun is 2x compute per step but highest quality. Use for final renders." }, "anime_pony": { "description": "Pony Diffusion V6 XL author settings.", "steps": 25, "cfg": 7.0, "sampler": "euler_ancestral", "scheduler": "normal", "clip_skip": 2, "notes": "CLIP SKIP 2 IS CRITICAL for Pony — model outputs blobs without it. No neg prompt needed. Use score_9, score_8_up tags." }, "anime_sharp": { "description": "Sharp anime with SDE sampler.", "steps": 25, "cfg": 7.5, "sampler": "dpmpp_sde", "scheduler": "karras", "notes": "DPM++ SDE Karras for sharper anime. Slower than 2M." } }, "resolutions": { "square": [1024, 1024], "portrait_3_4": [896, 1152], "portrait_9_16": [768, 1344], "landscape_4_3": [1152, 896], "landscape_16_9": [1344, 768] } }, "illustrious": { "display_name": "Illustrious XL", "architecture": "sdxl", "clip_type": "sdxl", "prompt_style": "booru_tags", "prompt_notes": "Use danbooru tags: 1girl, solo, long_hair, blue_eyes. Quality: masterpiece, best quality, absurdres. CFG > 7.5 causes oversaturation, < 3 loses color.", "presets": { "default": { "description": "Community standard Illustrious settings.", "steps": 25, "cfg": 4.5, "sampler": "euler_ancestral", "scheduler": "simple", "notes": "CFG 4.5-5.0 is the sweet spot. euler_ancestral is community favorite." }, "detailed": { "steps": 30, "cfg": 5.0, "sampler": "dpmpp_2m", "scheduler": "karras", "notes": "More consistent/detailed. For complex compositions, increase steps to 40." }, "sharp_shading": { "steps": 15, "cfg": 5.0, "sampler": "dpmpp_2s_ancestral", "scheduler": "karras", "notes": "Enhanced shading detail. Watch for noise in flat color areas." } }, "resolutions": { "optimal_range": "1024-1536px per side" } }, "flux": { "display_name": "Flux.1", "architecture": "flux", "clip_type": "flux", "prompt_style": "natural_language", "prompt_notes": "Natural language descriptions. No quality tags needed. Detailed, descriptive prompts work best.", "notes": "Flux uses FluxGuidance node (guidance=3.5), NOT KSampler CFG. Set KSampler CFG=1.0 always.", "presets": { "dev": { "description": "Flux.1-dev standard.", "steps": 20, "cfg": 1.0, "sampler": "euler", "scheduler": "simple", "guidance": 3.5, "notes": "Guidance 3.5 via FluxGuidance node. Steps 20-28. Short prompts: guidance 3.5-4.0, long prompts: 1.0-1.5." }, "schnell": { "description": "Flux.1-schnell (1-4 steps, no LoRA needed).", "steps": 4, "cfg": 1.0, "sampler": "euler", "scheduler": "simple" }, "flux2_turbo": { "description": "Flux 2 with turbo LoRA.", "steps": 4, "cfg": 1.0, "sampler": "euler", "scheduler": "simple", "lora": { "name": "flux2-turbo-lora.safetensors", "strength": 1.0 } } }, "resolutions": { "square": [1024, 1024], "portrait_3_4": [896, 1152], "landscape_4_3": [1152, 896] } }, "sd35": { "display_name": "Stable Diffusion 3.5", "architecture": "sd3", "presets": { "large": { "steps": 25, "cfg": 4.5, "sampler": "dpmpp_2m", "scheduler": "normal" }, "large_turbo": { "steps": 5, "cfg": 1.0, "sampler": "euler", "scheduler": "normal" }, "medium": { "steps": 28, "cfg": 4.5, "sampler": "euler", "scheduler": "normal" } } } }, "lightning_loras": { "_description": "Index of available lightning/turbo LoRAs.", "qwen_image_4step": { "file": "Qwen-Image-Lightning-4steps-V1.0.safetensors", "source": "https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning", "steps": 4, "compatible_with": ["qwen_image", "qwen_image_2512", "qwen_finetuned"], "strength": 1.0, "cfg": 1.0, "speedup": "12-25x" }, "qwen_image_8step": { "file": "Qwen-Image-Lightning-8steps-V1.0.safetensors", "source": "https://huggingface.co/lightx2v/Qwen-Image-2512-Lightning", "steps": 8, "compatible_with": ["qwen_image", "qwen_image_2512", "qwen_finetuned"], "strength": 1.0, "cfg": 1.0, "notes": "Better quality than 4-step. Use CFG 2.5 for character detail." }, "qwen_edit_2511_4step": { "file": "Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors", "source": "https://huggingface.co/lightx2v/Qwen-Image-Edit-2511-Lightning", "steps": 4, "compatible_with": ["qwen_image_2511_edit"], "strength": 1.0, "cfg": 1.0, "speedup": "~10x", "notes": "Cannot combine with distilled model." }, "wuli_turbo_v3": { "file": "NOT_INSTALLED", "source": "https://huggingface.co/Wuli-art/Qwen-Image-2512-Turbo-LoRA", "steps": 4, "compatible_with": ["qwen_image_2512"], "strength": 1.0, "cfg": 1.0, "speedup": "20x", "notes": "Wuli-art V3.0 (Jan 2026). CFG-distilled. Also has 2-step and 8-step variants. May need download." }, "flux2_turbo": { "file": "flux2-turbo-lora.safetensors", "steps": 4, "compatible_with": ["flux"], "strength": 1.0, "cfg": 1.0 } }, "sampler_guide": { "_description": "Quick reference for sampler/scheduler by use case.", "general_fast": { "sampler": "euler", "scheduler": "simple", "notes": "Works everywhere. Default." }, "sdxl_realistic": { "sampler": "dpmpp_2m", "scheduler": "karras", "notes": "SDXL gold standard. AVOID Euler on SDXL." }, "sdxl_anime": { "sampler": "euler_ancestral", "scheduler": "normal", "notes": "Pony/anime SDXL. Clip skip 2 for Pony." }, "illustrious": { "sampler": "euler_ancestral", "scheduler": "simple", "notes": "CFG 4.5-5.0 sweet spot." }, "character_composition":{ "sampler": "euler_ancestral", "scheduler": "beta", "notes": "Multi-character scenes, varied compositions." }, "qwen_realistic_hq": { "sampler": "res_multistep", "scheduler": "sgm_uniform", "notes": "CopaxTimeless pick for Qwen." }, "z_image_sharp": { "sampler": "dpmpp_sde", "scheduler": "beta", "notes": "Sharpest Z-Image results (560-image test)." }, "z_image_beauty": { "sampler": "euler_ancestral", "scheduler": "beta", "notes": "Smooth skin, fashion/beauty." }, "z_image_turbo": { "sampler": "res_2s", "scheduler": "simple", "notes": "Z-Image Turbo distilled." } }, "_contributing": { "how_to_contribute": "Fork the repo, add your model/preset, submit a PR.", "required_fields": ["Model name + author", "Source URL", "At least one preset (steps/cfg/sampler/scheduler)", "Resolution if non-standard"], "optional_fields": ["Lightning LoRA compatibility", "Prompt style tips", "Known quirks", "img2img denoise range"], "contributors": [ { "name": "artokun", "role": "maintainer", "date": "2026-02-16" } ] } }