- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add artokun/comfyui-mcp --skill flux-txt2img -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add artokun/comfyui-mcp --skill flux-txt2img -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add artokun/comfyui-mcp --skill flux-txt2img -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add artokun/comfyui-mcp --skill flux-txt2img -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/artokun/comfyui-mcp/tree/HEAD/plugin/skills/flux-txt2img게시자 제공
Flux is a guidance-distilled diffusion model family from Black Forest Labs. It uses a separate FluxGuidance node instead of KSampler CFG (which must always be 1.0). Three variants are available locally:
flux2-vae.safetensors. Fast 4-step generation.Klein 9B vs Flux.1 Dev: Klein uses the Qwen3-8B text encoder (not T5XXL + CLIP-L). It has a different VAE (flux2-vae.safetensors). 9B distilled runs in 4 steps; 9B base needs ~50 steps at CFG 5.0. Fits in ~20GB VRAM with FP8.
Provides separate prompt fields for each text encoder:
{
"class_type": "CLIPTextEncodeFlux",
"inputs": {
"clip": ["<dual_clip>", 0],
"clip_l": "short prompt for CLIP-L",
"t5xxl": "detailed description for T5XXL",
"guidance": 3.5
}
}
clip_l captures key semantic features. t5xxl expands and refines descriptions. For simple use, put the same prompt in both fields. Guidance is built into this node, so no separate FluxGuidance is needed.
If using standard CLIPTextEncode instead of CLIPTextEncodeFlux, apply guidance separately:
{
"class_type": "FluxGuidance",
"inputs": {
"conditioning": ["<clip_text_encode>", 0],
"guidance": 3.5
}
}
Flux does not support traditional negative prompts (guidance-distilled, CFG=1.0). Use ConditioningZeroOut:
{
"class_type": "ConditioningZeroOut",
"inputs": { "conditioning": ["<positive_cond>", 0] }
}
Or use an empty CLIPTextEncode for the negative input.
The SRPO author recommends the ipndm/beta combo. Standard Flux settings (euler/simple) also work, but ipndm/beta gives better results with this fine-tune.
Flux operates at ~1 megapixel natively. Dimensions should be multiples of 8.
Natural language descriptions. No quality tags needed (unlike SDXL/Illustrious). Detailed, descriptive prompts work best.
Good: "A young woman with auburn hair sits at a sunlit cafe in Paris, wearing a cream linen blazer, soft bokeh background, shot on Sony A7III 85mm f/1.4"
Bad: "masterpiece, best quality, 1girl, cafe, paris"
{
"1": { "class_type": "UNETLoader", "inputs": { "unet_name": "flux.1-dev-SRPO-BFL-bf16.safetensors", "weight_dtype": "default" }},
"2": { "class_type": "DualCLIPLoader", "inputs": { "clip_name1": "t5xxl_fp8_e4m3fn.safetensors", "clip_name2": "clip_l.safetensors", "type": "flux" }},
"3": { "class_type": "VAELoader", "inputs": { "vae_name": "ae.safetensors" }},
"4": { "class_type": "CLIPTextEncodeFlux", "inputs": {
"clip": ["2", 0],
"clip_l": "<short prompt>",
"t5xxl": "<detailed prompt>",
"guidance": 3.5
}},
"5": { "class_type": "ConditioningZeroOut", "inputs": { "conditioning": ["4", 0] }},
"6": { "class_type": "EmptyLatentImage", "inputs": { "width": 896, "height": 1152, "batch_size": 1 }},
"7": { "class_type": "KSampler", "inputs": {
"model": ["1", 0],
"positive": ["4", 0],
"negative": ["5", 0],
"latent_image": ["6", 0],
"seed": 42, "steps": 20, "cfg": 1, "sampler_name": "ipndm", "scheduler": "beta", "denoise": 1
}},
"8": { "class_type": "VAEDecode", "inputs": { "samples": ["7", 0], "vae": ["3", 0] }},
"9": { "class_type": "SaveImage", "inputs": { "images": ["8", 0], "filename_prefix": "flux_srpo" }}
}
{
"1": { "class_type": "UNETLoader", "inputs": { "unet_name": "bigLove_klein1.safetensors", "weight_dtype": "default" }},
"2": { "class_type": "CLIPLoader", "inputs": { "clip_name": "qwen_3_8b_fp8mixed.safetensors", "type": "flux2" }},
"3": { "class_type": "VAELoader", "inputs": { "vae_name": "flux2-vae.safetensors" }},
"4": { "class_type": "CLIPTextEncode", "inputs": { "clip": ["2", 0], "text": "<prompt>" }},
"5": { "class_type": "ConditioningZeroOut", "inputs": { "conditioning": ["4", 0] }},
"6": { "class_type": "EmptyFlux2LatentImage", "inputs": { "width": 1024, "height": 1024, "batch_size": 1 }},
"7": { "class_type": "KSampler", "inputs": {
"model": ["1", 0],
"positive": ["4", 0],
"negative": ["5", 0],
"latent_image": ["6", 0],
"seed": 42, "steps": 4, "cfg": 1, "sampler_name": "euler", "scheduler": "simple", "denoise": 1
}},
"8": { "class_type": "VAEDecode", "inputs": { "samples": ["7", 0], "vae": ["3", 0] }},
"9": { "class_type": "SaveImage", "inputs": { "images": ["8", 0], "filename_prefix": "flux_klein" }}
}
Klein uses a single CLIPLoader (not DualCLIPLoader) with type: "flux2" and the Qwen3-8B text encoder from text_encoders/. The CLIP loader path resolves from models/text_encoders/.
Flux-2-specific gotchas, all of which fail at the KSampler rather than the loader, so the error points at the wrong node:
type must be flux2, not flux. Both values exist in the CLIPLoader enum, so flux loads without complaint and then dies during sampling.EmptyFlux2LatentImage, not EmptyLatentImage. Flux 2 uses a different latent channel count.qwen_3_8b* from Comfy-Org/vae-text-encorder-for-flux-klein-9b). The similarly-named qwen_3_4b ships in the klein-4b repo and is for the 4B model. Mismatching them raises mat1 and mat2 shapes cannot be multiplied (512x7680 and 12288x4096), where 7680 = 2560x3 (4B hidden size) and 12288 = 4096x3 (8B). It reads as a confusing CLIP error rather than a wrong-file error.{
"1": { "class_type": "UNETLoader", "inputs": { "unet_name": "flux.1-dev-SRPO-BFL-bf16.safetensors", "weight_dtype": "default" }},
"2": { "class_type": "LoraLoaderModelOnly", "inputs": { "model": ["1", 0], "lora_name": "flux2-turbo-lora.safetensors", "strength_model": 1.0 }},
"3": { "class_type": "DualCLIPLoader", "inputs": { "clip_name1": "t5xxl_fp8_e4m3fn.safetensors", "clip_name2": "clip_l.safetensors", "type": "flux" }},
"4": { "class_type": "VAELoader", "inputs": { "vae_name": "ae.safetensors" }},
"5": { "class_type": "CLIPTextEncodeFlux", "inputs": {
"clip": ["3", 0],
"clip_l": "<short prompt>",
"t5xxl": "<detailed prompt>",
"guidance": 3.5
}},
"6": { "class_type": "ConditioningZeroOut", "inputs": { "conditioning": ["5", 0] }},
"7": { "class_type": "EmptyLatentImage", "inputs": { "width": 1024, "height": 1024, "batch_size": 1 }},
"8": { "class_type": "KSampler", "inputs": {
"model": ["2", 0],
"positive": ["5", 0],
"negative": ["6", 0],
"latent_image": ["7", 0],
"seed": 42, "steps": 4, "cfg": 1, "sampler_name": "euler", "scheduler": "simple", "denoise": 1
}},
"9": { "class_type": "VAEDecode", "inputs": { "samples": ["8", 0], "vae": ["4", 0] }},
"10": { "class_type": "SaveImage", "inputs": { "images": ["9", 0], "filename_prefix": "flux_turbo" }}
}
Apply Flux LoRAs with LoraLoaderModelOnly between UNET and KSampler:
{
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": ["<unet_or_previous_lora>", 0],
"lora_name": "<lora_file>.safetensors",
"strength_model": 1.0
}
}
Klein 9B LoRAs go in the loras/Flux.2 Klein 9B/ subfolder:
klein_slider_detail.safetensors, a detail slider LoRAclear_vram before switching to Flux from another model familyCLIPTextEncodeFlux or FluxGuidancepacks/ and observed renders; not a vendor prompting guide.Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns
---name: flux-txt2imgdescription: Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and…---# plugin/skills/flux-txt2img/SKILL.mdFAQ
게시자에게서 plugin/skills/flux-txt2img/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/artokun/comfyui-mcp에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.