Agent skill

Model Compatibility

Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models

MITAuto-check passedAI & LLM Engineering

Install Model Compatibility

skills CLI

$ npx skills add artokun/comfyui-mcp --skill model-compatibility -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install artokun/comfyui-mcp model-compatibility --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/artokun/comfyui-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/model-compatibility .claude/skills/model-compatibility && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "model-compatibility" agent skill from https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/model-compatibility into .claude/skills/model-compatibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compatibility", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/model-compatibility

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add artokun/comfyui-mcp --skill model-compatibility -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install artokun/comfyui-mcp model-compatibility --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/artokun/comfyui-mcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/model-compatibility .agents/skills/model-compatibility && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "model-compatibility" agent skill from https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/model-compatibility into .agents/skills/model-compatibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compatibility", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add artokun/comfyui-mcp --skill model-compatibility -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install artokun/comfyui-mcp model-compatibility --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/artokun/comfyui-mcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/model-compatibility .cursor/skills/model-compatibility && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "model-compatibility" agent skill from https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/model-compatibility into .cursor/skills/model-compatibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compatibility", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/artokun/comfyui-mcp.git --path plugin/skills/model-compatibility

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add artokun/comfyui-mcp --skill model-compatibility -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install artokun/comfyui-mcp model-compatibility --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/artokun/comfyui-mcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/model-compatibility .gemini/skills/model-compatibility && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "model-compatibility" agent skill from https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/model-compatibility into .gemini/skills/model-compatibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compatibility", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install artokun/comfyui-mcp model-compatibility

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add artokun/comfyui-mcp --skill model-compatibility -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/artokun/comfyui-mcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/model-compatibility .github/skills/model-compatibility && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "model-compatibility" agent skill from https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/model-compatibility into .github/skills/model-compatibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compatibility", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add artokun/comfyui-mcp --skill model-compatibility -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install artokun/comfyui-mcp model-compatibility --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/artokun/comfyui-mcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/model-compatibility .opencode/skills/model-compatibility && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "model-compatibility" agent skill from https://github.com/artokun/comfyui-mcp/tree/main/plugin/skills/model-compatibility into .opencode/skills/model-compatibility/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-compatibility", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: model-compatibility
GitHub stars: 795
Token cost: ~4k tokens
SKILL.md length: 1,560 words
Files: 1
Skills in repo: 42
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models

Tasks that involve Diffusion and image models
SKILL.md covers Stable Diffusion 1.5 (SD 1.5), SDXL (Stable Diffusion XL), Flux (Flux.1) and Stable Diffusion 3 / 3.5 (SD3)
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
Tasks that involve Fine-tuning

What it does

Model Compatibility is an agent skill from artokun/comfyui-mcp. Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models

Its SKILL.md is about 4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering Diffusion and image models and Fine-tuning. It works with Stable Diffusion. The repository describes itself as: Local-first, agent-native control plane for ComfyUI — MCP server + sidebar agent that generates images, video & audio, authors and runs workflows, and edits your live graph in… The licence is MIT.

When your agent uses it

Tasks that involve Diffusion and image models
Tasks that involve Fine-tuning

Example prompts

“/model-compatibility”

What it can do on your machine

Read from SKILL.md and the folder at commit 6ad6fc0. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Model Compatibility loads about 4k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 1,560 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~46
When it runs · the whole SKILL.md, loaded when a task matches: ~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from artokun/comfyui-mcp at commit 6ad6fc0, republished under its MIT licence (© artokun). 1,560 words, ~4,040 tokens.

Download SKILL.mdSave it as .claude/skills/model-compatibility/SKILL.md (or your agent's skills folder).

name: model-compatibility
description: Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models
globs: **/*.json

ComfyUI Model Compatibility Matrix

Stable Diffusion 1.5 (SD 1.5)

Overview

The original widely-adopted Stable Diffusion model. Huge ecosystem of fine-tunes, LoRAs, ControlNets, and embeddings. Still the most compatible and lightweight model family.

Configuration

Parameter	Value
Loader	`CheckpointLoaderSimple`
Native Resolution	512x512
Supported Resolutions	512x512, 512x768, 768x512, 768x768 (some fine-tunes)
VAE	Built-in or external (`vae-ft-mse-840000-ema-pruned.safetensors`)
CLIP	Single CLIP-L (output index 1 from checkpoint)
Text Encoder Node	`CLIPTextEncode`
CFG Range	7-12 (typical: 7.5)
Negative Prompt	Yes — very important for quality
Steps	20-30 (standard samplers)
Sampler	All standard samplers: `euler`, `euler_ancestral`, `dpmpp_2m`, `dpmpp_sde`, `ddim`
Scheduler	`normal`, `karras`
Denoise	1.0 (txt2img), 0.5-0.8 (img2img)
VRAM (FP16)	~2-3GB

Workflow Pattern

CheckpointLoaderSimple → MODEL(0), CLIP(1), VAE(2)
  CLIP(1) → CLIPTextEncode (positive) → CONDITIONING
  CLIP(1) → CLIPTextEncode (negative) → CONDITIONING
EmptyLatentImage (width=512, height=512) → LATENT
KSampler (cfg=7.5, steps=20, sampler="euler", scheduler="normal") → LATENT
VAEDecode → IMAGE
SaveImage

VAE Notes

Most SD 1.5 checkpoints have a built-in VAE, but it's often mediocre
Recommended: Use external vae-ft-mse-840000-ema-pruned.safetensors for better color accuracy
Load via VAELoader node and connect to VAEDecode
FP16 VAE can produce NaN on some images. FP32 VAE is more stable

ControlNet Compatibility

SD 1.5 has the largest ControlNet ecosystem:

ControlNet	Model File Pattern	Notes
Canny	`control_v11p_sd15_canny`	Edge detection
Depth	`control_v11f1p_sd15_depth`	Depth map
OpenPose	`control_v11p_sd15_openpose`	Skeleton/pose
Scribble	`control_v11p_sd15_scribble`	Hand-drawn lines
Lineart	`control_v11p_sd15_lineart`	Clean lines
Softedge	`control_v11p_sd15_softedge`	Soft edges (HED)
Normal	`control_v11p_sd15_normalbae`	Normal maps
Seg	`control_v11p_sd15_seg`	Semantic segmentation
Tile	`control_v11f1e_sd15_tile`	Tile/upscale guidance
Inpaint	`control_v11p_sd15_inpaint`	Inpainting guidance
IP-Adapter	`ip-adapter_sd15`	Image prompt

LoRA Compatibility

SD 1.5 LoRAs ONLY work with SD 1.5 base models
Format: .safetensors in models/loras/
Loader: LoraLoader node, which connects between checkpoint and CLIPTextEncode
Strength range: 0.5-1.0 (higher can cause artifacts)

SDXL (Stable Diffusion XL)

Overview

Major upgrade from SD 1.5 with dual CLIP encoders, higher native resolution, and better prompt understanding. Includes Turbo and Lightning variants for fast generation.

Configuration — SDXL 1.0 (Base)

Parameter	Value
Loader	`CheckpointLoaderSimple`
Native Resolution	1024x1024
Supported Resolutions	1024x1024, 832x1216, 1216x832, 896x1152, 1152x896, 768x1344, 1344x768
VAE	Built-in (SDXL has good integrated VAE)
CLIP	Dual CLIP: CLIP-L + CLIP-G
Text Encoder Node	`CLIPTextEncode` (unified) or `CLIPTextEncodeSDXL` (separate G/L)
CFG Range	5-10 (typical: 7.0)
Negative Prompt	Yes — moderately important
Steps	20-40
Sampler	`euler`, `euler_ancestral`, `dpmpp_2m`, `dpmpp_sde`
Scheduler	`normal`, `karras`
Denoise	1.0 (txt2img), 0.5-0.8 (img2img)
VRAM (FP16)	~6-7GB

Configuration — SDXL Turbo

Parameter	Value
Loader	`CheckpointLoaderSimple`
Resolution	512x512 (optimized for lower res)
CFG	1.0-2.0
Steps	1-4
Sampler	`euler_ancestral`
Scheduler	`normal`
Negative Prompt	Minimal or empty
Denoise	1.0

Configuration — SDXL Lightning

Parameter	Value
Loader	`CheckpointLoaderSimple` + `LoraLoader` (Lightning LoRA)
Resolution	1024x1024
CFG	1.0-2.0
Steps	4-8 (match the Lightning variant: 2-step, 4-step, 8-step)
Sampler	`euler`
Scheduler	`sgm_uniform`
Negative Prompt	Empty or minimal
Special	Requires matching Lightning LoRA for the step count

SDXL Refiner

The optional SDXL refiner model does a second pass to improve fine details:

CheckpointLoaderSimple (base) → KSampler (steps=25, start=0, end=20)
CheckpointLoaderSimple (refiner) → KSampler (steps=25, start=20, end=25)

The refiner uses KSamplerAdvanced with start_at_step and end_at_step
Typically run the base for 80% of steps, refiner for the last 20%
Refiner checkpoint: sd_xl_refiner_1.0.safetensors

Workflow Pattern

CheckpointLoaderSimple → MODEL(0), CLIP(1), VAE(2)
  CLIP(1) → CLIPTextEncode (positive) → CONDITIONING
  CLIP(1) → CLIPTextEncode (negative) → CONDITIONING
EmptyLatentImage (width=1024, height=1024) → LATENT
KSampler (cfg=7.0, steps=25, sampler="dpmpp_2m", scheduler="karras") → LATENT
VAEDecode → IMAGE
SaveImage

ControlNet Compatibility

SDXL ControlNets are separate from SD 1.5 ControlNets:

ControlNet	Model File Pattern	Notes
Canny	`control-lora-canny-rank256` or `diffusers_xl_canny`	Often LoRA-based
Depth	`control-lora-depth-rank256` or `diffusers_xl_depth`
T2I-Adapter	`t2i-adapter-*-sdxl`	Lighter alternative to ControlNet
IP-Adapter	`ip-adapter_sdxl`	Image prompt adapter
InstantID	`instantid-*`	Face-specific

LoRA Compatibility

SDXL LoRAs ONLY work with SDXL base models, NOT with SD 1.5
Same LoraLoader node as SD 1.5
Lightning LoRAs are SDXL LoRAs that enable few-step generation

Flux (Flux.1)

Overview

Black Forest Labs' model with a T5-XXL text encoder. Produces high-quality images without negative prompts. Available in schnell (fast) and dev (quality) variants.

Configuration — Flux Schnell

Parameter	Value
Loader	`CheckpointLoaderSimple` (single-file) or `DualCLIPLoader` + `UNETLoader` + `VAELoader` (split)
Native Resolution	1024x1024 (flexible aspect ratios)
Supported Resolutions	Flexible: 512x512 to 2048x2048, any aspect ratio
VAE	Separate Flux VAE (`ae.safetensors`) — NOT shared with SD models
CLIP	T5-XXL + CLIP-L via `DualCLIPLoader`
Text Encoder Node	`CLIPTextEncode` (single combined)
CFG	1.0 (MUST be 1.0 — higher values cause severe artifacts)
Negative Prompt	NONE — do not connect negative conditioning
Steps	4
Sampler	`euler`
Scheduler	`simple` or `sgm_uniform`
Denoise	1.0
VRAM (FP16)	~24GB (FP8: ~12GB)

Configuration — Flux Dev

Parameter	Value
Same as Schnell except:
Steps	20-50 (typical: 30)
Scheduler	`sgm_uniform`
VRAM (FP16)	~24GB (FP8: ~12GB)

Loading Methods

Method 1: Single Checkpoint (simplest)

CheckpointLoaderSimple (ckpt_name="flux1-schnell.safetensors")
  → MODEL(0), CLIP(1), VAE(2)

Method 2: Split Components (recommended for FP8)

UNETLoader (unet_name="flux1-schnell-fp8.safetensors") → MODEL
DualCLIPLoader (clip_name1="t5xxl_fp16.safetensors", clip_name2="clip_l.safetensors", type="flux") → CLIP
VAELoader (vae_name="ae.safetensors") → VAE

CRITICAL Rules

CFG MUST be 1.0. Flux uses guidance embedded in the model, not classifier-free guidance
No negative prompt. Empty string or don't connect the negative input at all
Separate VAE required. Flux uses its own VAE (ae.safetensors), not SD VAEs
FP8 strongly recommended for 24GB cards. FP16 Flux barely fits in 24GB VRAM
T5-XXL encoder can be loaded in FP8 to save additional VRAM
Kitchen quant column (this GPU): kitchen action:"status" reports gpu.fp8 (SM ≥ 8.9, Ada), gpu.nvfp4 and gpu.mxfp8 (SM ≥ 10.0, Blackwell). A UNETLoader on weight_dtype: default with an unquantized file and kitchen present is panel_kitchen action:"assess" rec fp8_unet_fast (set fp8_e4m3fn_fast). An NVFP4 sibling on disk is rec nvfp4_swap. MXFP8 is reported in status but not recommended until a loader path exposes it.

Workflow Pattern

UNETLoader (flux fp8) → MODEL
DualCLIPLoader (t5xxl + clip_l, type="flux") → CLIP
VAELoader (ae.safetensors) → VAE

CLIPTextEncode (positive prompt) → CONDITIONING
  (no negative CLIPTextEncode needed)

EmptyLatentImage (width=1024, height=1024) → LATENT

KSampler (cfg=1.0, steps=4, sampler="euler", scheduler="simple") → LATENT
VAEDecode (vae from VAELoader) → IMAGE
SaveImage

ControlNet Compatibility

Flux ControlNets are model-specific:

ControlNet	Notes
Flux ControlNet (Canny)	Specific Flux-compatible ControlNet
Flux ControlNet (Depth)	Specific Flux-compatible ControlNet
InstantX ControlNets	Community Flux ControlNets
Flux IP-Adapter	Image prompt for Flux

SD 1.5 and SDXL ControlNets do NOT work with Flux.

LoRA Compatibility

Flux LoRAs ONLY work with Flux models
Typically loaded via LoraLoader same as SD models
Flux LoRA ecosystem is smaller than SD 1.5/SDXL but growing
Some Flux LoRAs require specific trigger words

Stable Diffusion 3 / 3.5 (SD3)

Overview

Stability AI's next-generation model with triple CLIP architecture. Better prompt adherence and longer prompt support via T5-XXL.

Configuration

Parameter	Value
Loader	`CheckpointLoaderSimple` or triple-clip loader
Native Resolution	1024x1024
VAE	Built-in (integrated)
CLIP	Triple: CLIP-L + CLIP-G + T5-XXL
Text Encoder Node	`CLIPTextEncode` or `CLIPTextEncodeSD3`
CFG Range	4-7 (typical: 5.0)
Negative Prompt	Minimal — SD3 needs very little negative guidance
Steps	20-30
Sampler	`euler`, `dpmpp_2m`
Scheduler	`sgm_uniform`, `normal`
Denoise	1.0 (txt2img)
Shift	Some samplers support a shift parameter for SD3
VRAM (FP16)	~12GB (without T5-XXL: ~6GB)

Show full SKILL.md (617 more words)Show less

Triple CLIP Loading

CheckpointLoaderSimple → MODEL(0), CLIP(1), VAE(2)

Or for separate CLIP control:

DualCLIPLoader (clip_l + clip_g) → CLIP
CLIPLoader (t5xxl) → CLIP

Key Differences from SD 1.5/SDXL

Much better text rendering capabilities
Handles spatial relationships better ("cat on the left, dog on the right")
T5-XXL enables long, detailed prompts (no 77-token limit concern)
Lower CFG values (4-7 vs 7-12)
Minimal negative prompting needed
shift parameter in sampling affects noise schedule

ControlNet Compatibility

SD3-specific ControlNets are limited
Check for SD3-compatible community ControlNets
SD 1.5 and SDXL ControlNets do NOT work with SD3

LTXV (Video Models)

Overview

Latent video diffusion models for text-to-video and image-to-video generation. VRAM-intensive.

Configuration

Parameter	Value
Loader	Special video checkpoint loader (varies by node pack)
Resolution	512x512 or 768x768 per frame (depends on model)
Frames	16-64 (depends on VRAM)
FPS	8-24
VRAM	20GB+ FP16, ~6-10GB FP8
Key Warning	Can OOM on 24GB VRAM — always use FP8 quantized models

VRAM Management

Always use FP8 quantized models on 24GB cards
Reduce frame count if OOM persists
Lower resolution helps a lot
Close other GPU-using applications
Consider --lowvram flag for ComfyUI

Cross-Family Compatibility Rules

LoRA Compatibility

LoRAs are model-family specific and are NOT interchangeable:

LoRA Trained For	Works With	Does NOT Work With
SD 1.5	SD 1.5 and its fine-tunes	SDXL, Flux, SD3
SDXL	SDXL and its fine-tunes	SD 1.5, Flux, SD3
Flux	Flux models only	SD 1.5, SDXL, SD3
SD3	SD3/3.5 models only	SD 1.5, SDXL, Flux

Using a LoRA with the wrong base model will produce garbage images or errors.

ControlNet Compatibility

ControlNets are also model-family specific:

ControlNet Trained For	Works With	Does NOT Work With
SD 1.5 (v1.1 series)	SD 1.5 base + fine-tunes	SDXL, Flux, SD3
SDXL	SDXL base + fine-tunes	SD 1.5, Flux, SD3
Flux	Flux models only	SD 1.5, SDXL, SD3

VAE Compatibility

VAE	Compatible Models	Notes
`vae-ft-mse-840000-ema-pruned`	SD 1.5 family	Best external VAE for SD 1.5
SDXL built-in VAE	SDXL family	Good quality, no external needed
`sdxl_vae.safetensors`	SDXL family	External SDXL VAE option
`ae.safetensors` (Flux VAE)	Flux only	Required for Flux, incompatible with SD
SD3 built-in VAE	SD3 family	Integrated, no external needed

Rule: Never mix VAEs across model families. An SD 1.5 VAE decoding Flux latents will produce garbage.

Embedding/Textual Inversion Compatibility

Embedding Type	Compatible Models
SD 1.5 embeddings	SD 1.5 family only
SDXL embeddings	SDXL family only
Flux/SD3	Generally don't use traditional embeddings

Sampler/Scheduler Compatibility

Most samplers work across all models, but some combinations are optimal:

Model	Best Sampler	Best Scheduler	Notes
SD 1.5	`euler_ancestral`, `dpmpp_2m`	`karras`, `normal`	All standard samplers work
SDXL	`dpmpp_2m`, `euler`	`karras`, `normal`	Same as SD 1.5
SDXL Turbo	`euler_ancestral`	`normal`	Must use 1-4 steps
SDXL Lightning	`euler`	`sgm_uniform`	Must match step count to LoRA
Flux Schnell	`euler`	`simple`	4 steps only
Flux Dev	`euler`	`sgm_uniform`	20-50 steps
SD3	`euler`, `dpmpp_2m`	`sgm_uniform`, `normal`	Lower CFG needed

Quick Decision Guide

Choosing a Model

Use Case	Recommended Model	Why
Maximum ecosystem/community support	SD 1.5	Most LoRAs, ControlNets, embeddings
High quality, good prompt following	SDXL	Best balance of quality and ecosystem
Fastest generation	SDXL Turbo/Lightning	1-4 steps
Best prompt understanding	Flux Dev	T5-XXL encoder, natural language
Fast + good quality	Flux Schnell	4 steps, no negative needed
Text in images	SD3.5	Best text rendering
Low VRAM (<6GB)	SD 1.5	Smallest memory footprint
Video generation	LTXV / AnimateDiff	Only options for video

Choosing Resolution

Model	Minimum	Recommended	Maximum (before OOM on 24GB)
SD 1.5	256x256	512x512	768x768
SDXL	512x512	1024x1024	1536x1536
Flux (FP8)	512x512	1024x1024	2048x2048
Flux (FP16)	512x512	1024x1024	1024x1024 (tight)
SD3	512x512	1024x1024	1536x1536

Going below the recommended resolution produces blurry/low-quality results. Going above the maximum risks OOM errors or quality degradation (tiling artifacts).

Sources

Official: none found as a vendor pairing matrix. Kitchen hardware gates: ComfyUI comfy/model_management.py (supports_fp8_compute, supports_nvfp4_compute, supports_mxfp8_compute); UNETLoader weight_dtype in nodes.py.
Empirical: base-model / VAE / CLIP pairing rules from observed load failures.

Files

Just SKILL.md in plugin/skills/model-compatibility of artokun/comfyui-mcp.

Open the folder on GitHubat commit 6ad6fc0

Compare with similar skills

Model Compatibility next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Model Compatibility compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Model Compatibility this skillartokun/comfyui-mcp	795	—	~4k	Automated safety check: Pass	MIT	3 days ago
Diffusers Ascend Pipelineascend-ai-coding/awesome-ascend-skills	174	—	~3.2k	Automated safety check: Pass	None	today
Automatic1111majiayu000/claude-skill-registry	666	1 repos	~1.6k	Automated safety check: Pass	Apache-2.0	today
Castguaardvark/guaardvark	255	—	~673	Automated safety check: Pass	MIT	today
Workflow Template BuilderMooshieblob1/MooshieUI	207	—	~640	Automated safety check: Pass	AGPL-3.0	yesterday
Flux2 Lora TrainingAnastasiyaW/codex-claude-code-config	154	—	~4.5k	Automated safety check: Pass	MIT	today

Similar skills

Diffusers Ascend Pipeline
ascend-ai-coding/awesome-ascend-skills
Diffusers Pipeline 推理指南，用于华为昇腾 NPU。覆盖环境预检、通用 Pipeline 推理（图像/视频模型）、内存优化（CPU offload、attention slicing、VAE slicing）、LoRA 加载与融合、多卡推理和按版本检索 Diffusers API。用户一旦提到在昇腾 NPU 上运行 FLUX、SDXL、Wan、CogVideoX 等…
174 GitHub stars~3.2k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Automatic1111
majiayu000/claude-skill-registry
Feature-rich Stable Diffusion Web UI for image generation. An agent skill from majiayu000/claude-skill-registry.
666 GitHub starsUsed in 1 repo~1.6k tokens
AI & LLM EngineeringAuto-check passed
Cast
guaardvark/guaardvark
Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training).
255 GitHub stars~673 tokensUpdated today
AI & LLM EngineeringAuto-check passed
Workflow Template Builder
Mooshieblob1/MooshieUI
Builds or modifies ComfyUI workflow JSON templates in MooshieUI's Rust backend (src-tauri/src/templates).
207 GitHub stars~640 tokensUpdated yesterday
AI & LLM EngineeringAuto-check passed
Flux2 Lora Training
AnastasiyaW/codex-claude-code-config
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets, trainer-version contracts, and held-out fidelity checks.
154 GitHub stars~4.5k tokensUpdated today
AI & LLM EngineeringAuto-check passed
Diffusion Engineering
AnastasiyaW/codex-claude-code-config
Практическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти.
154 GitHub stars~1.2k tokensUpdated today
AI & LLM EngineeringAuto-check passed

More from artokun/comfyui-mcp

All 42 skills in this repo

AI Toolkit Trainer
artokun/comfyui-mcp
Train custom LoRAs with ostris AI-Toolkit. An agent skill from artokun/comfyui-mcp.
795 GitHub stars~2.7k tokensUpdated 3 days ago
Auto-check passed
Anima Base
artokun/comfyui-mcp
Anime/illustration text-to-image (ANIMA 1.0, ~2B Cosmos DiT).
795 GitHub stars~4k tokensUpdated 3 days ago
Auto-check passed
Civitai
artokun/comfyui-mcp
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally.
795 GitHub stars~1.1k tokensUpdated 3 days ago
Auto-check passed
Color Correction
artokun/comfyui-mcp
Diagnose and fix video/image color OBJECTIVELY with the getimage (action:"analyzecolor") tool (scopes/stats such as black/white points, contrast, saturation, clipping, cast) instead of eyeballing a…
795 GitHub stars~2.4k tokensUpdated 3 days ago
Auto-check passed
Comfyui Frontend Extensions
artokun/comfyui-mcp
Authoring ComfyUI v2 frontend extensions with @comfyorg/extension-api, covering defineNode/defineExtension/defineWidget, shell UI (sidebar tabs, commands, hotkeys), typed events, and handles.
795 GitHub stars~5.4k tokensUpdated 3 days ago
Auto-check passed
Comfyui Launch Flags
artokun/comfyui-mcp
Pick the right ComfyUI startup flags for VRAM, attention, caching, and speed.
795 GitHub stars~3.1k tokensUpdated 3 days ago
Auto-check passed

Works with

Stable Diffusion

Questions about Model Compatibility

What does Model Compatibility do?

Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models. Model Compatibility is an agent skill from artokun/comfyui-mcp.

When should I use Model Compatibility?

Model Compatibility fits situations like: tasks that involve Diffusion and image models; tasks that involve Fine-tuning.

How do I install Model Compatibility in Claude Code?

Run `npx skills add artokun/comfyui-mcp --skill model-compatibility -a claude-code`. Or copy the skill folder (plugin/skills/model-compatibility in artokun/comfyui-mcp) into .claude/skills/model-compatibility in your project. Claude Code loads it when a task matches its description.

How do I install Model Compatibility in Codex?

Run `npx skills add artokun/comfyui-mcp --skill model-compatibility -a codex`. Or copy the skill folder (plugin/skills/model-compatibility in artokun/comfyui-mcp) into .agents/skills/model-compatibility in your project. Codex loads it when a task matches its description.

Can I use Model Compatibility in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add artokun/comfyui-mcp --skill model-compatibility -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-compatibility, .gemini/skills/model-compatibility, .github/skills/model-compatibility and .opencode/skills/model-compatibility in your project.

What does Model Compatibility need to run?

SKILL.md names no scripts, command-line tools or credentials: Model Compatibility is instructions for the agent only.

Does Model Compatibility access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Model Compatibility safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Model Compatibility use?

Model Compatibility is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Model Compatibility use?

About 4k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Model Compatibility?

Skills that share tags, products or a category with Model Compatibility: Diffusers Ascend Pipeline (ascend-ai-coding/awesome-ascend-skills, 174 stars), Automatic1111 (majiayu000/claude-skill-registry, 666 stars), Cast (guaardvark/guaardvark, 255 stars) and Workflow Template Builder (Mooshieblob1/MooshieUI, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Model Compatibility?

artokun (a GitHub user) maintains it in artokun/comfyui-mcp, which has 795 GitHub stars. The repository holds 42 skills in this directory. The repository was last updated on October 5, 2026.

Source: artokun/comfyui-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Model Compatibility

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

ComfyUI Model Compatibility Matrix

Stable Diffusion 1.5 (SD 1.5)

Overview

Configuration

Workflow Pattern

VAE Notes

ControlNet Compatibility

LoRA Compatibility

SDXL (Stable Diffusion XL)

Overview

Configuration — SDXL 1.0 (Base)

Configuration — SDXL Turbo

Configuration — SDXL Lightning

SDXL Refiner

Workflow Pattern

ControlNet Compatibility

LoRA Compatibility

Flux (Flux.1)

Overview

Configuration — Flux Schnell

Configuration — Flux Dev

Loading Methods

CRITICAL Rules

Workflow Pattern

ControlNet Compatibility

LoRA Compatibility

Stable Diffusion 3 / 3.5 (SD3)

Overview

Configuration

Triple CLIP Loading

Key Differences from SD 1.5/SDXL

ControlNet Compatibility

LTXV (Video Models)

Overview

Configuration

VRAM Management

Cross-Family Compatibility Rules

LoRA Compatibility

ControlNet Compatibility

VAE Compatibility

Embedding/Textual Inversion Compatibility

Sampler/Scheduler Compatibility

Quick Decision Guide

Choosing a Model

Choosing Resolution

Sources

Files

Compare with similar skills

Similar skills

More from artokun/comfyui-mcp

Related

Questions about Model Compatibility