Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add artokun/comfyui-mcp --skill flux-txt2imggit clone --depth 1 https://github.com/artokun/comfyui-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/artokun/comfyui-mcp/flux-txt2img)<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/flux-txt2img"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/flux-txt2img/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/flux-txt2img"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/flux-txt2img.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.03992 |
| Opus 5 | $0.00022 | $0.01996 |
| Sonnet 5 | $0.00009 | $0.00798 |
| Haiku 4.5 | $0.00004 | $0.00399 |
Grade A, and why
flux-txt2img scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- flux-txt2img — 89% identical, 54 lines differ
How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flux Text-to-Image Workflows
Overview
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:
- Flux.1 Dev SRPO. Fine-tuned Flux.1 Dev with SRPO alignment. Uses DualCLIPLoader (T5XXL + CLIP-L). BF16 only.
- Flux 2 Klein 9B. Distilled Flux 2 variant. Uses single CLIPLoader (Qwen3-8B) +
flux2-vae.safetensors. Fast 4-step generation. - Flux 2 Turbo LoRA. Applied to Flux.1 Dev for 4-step generation.
Models
Flux.1 Dev SRPO
| Component | Node | Model | Notes |
|---|---|---|---|
| UNET | UNETLoader |
flux.1-dev-SRPO-BFL-bf16.safetensors |
22.7GB, BF16 only — FP8 produces broken results |
| CLIP | DualCLIPLoader (type=flux) |
clip_name1: t5xxl_fp8_e4m3fn.safetensors, clip_name2: clip_l.safetensors |
T5XXL (4.7GB) + CLIP-L (235MB) |
| VAE | VAELoader |
ae.safetensors |
Standard Flux VAE (320MB). Z-Image uses the same VAE architecture but different weights — its VAE is a separate file (z-image-ae.safetensors), not this one |
Flux 2 Klein 9B
| Component | Node | Model | Notes |
|---|---|---|---|
| UNET | UNETLoader |
bigLove_klein1.safetensors |
17.3GB, Klein 9B variant |
| CLIP | CLIPLoader (type=flux2) |
qwen_3_8b_fp8mixed.safetensors |
Qwen3-8B in text_encoders/ (8.3GB). Use flux2, NOT flux — both exist in the enum and flux fails at the sampler |
| VAE | VAELoader |
flux2-vae.safetensors |
Flux 2 specific VAE (321MB) |
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.
Flux 2 Turbo LoRA (applied to Flux.1 Dev)
| Component | Node | Model | Notes |
|---|---|---|---|
| LoRA | LoraLoaderModelOnly |
flux2-turbo-lora.safetensors |
2.6GB, strength 1.0 |
| Alt LoRA | LoraLoaderModelOnly |
Flux2TurboComfyv2.safetensors |
Community variant, same size |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 296 lines · 44 tokens per session scan A 5583e0e25123
flux-txt2img is a skill published in the GitHub repository artokun/comfyui-mcp (740 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 3,992 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
minimax-h3
Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off…
seedance
Use when writing or debugging prompts for ByteDance Seedance video models (Seedance 2.5, 2.0, 2.0 Mini, 1.5 Pro, 1.0) on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI, when a generated video drifts off the reference face, grows unwanted subtitles or watermarks, duplicates a character, jumps at an extension…
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
emotion-to-camera-language
A guide for turning vague visual feelings—such as cinematic, atmospheric, elegant, or healing—into concrete image or video prompt details. It uses lighting direction, depth of field, camera position, and the subject’s state.
comfyui-prompt-engineer
Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when generating or refining prompts for ComfyUI workflows.
comfyui-prompt-interview
Guided conversational interview to understand a user's creative vision before generating model-appropriate image prompts. Asks clarifying questions about subject, mood, style, and technical preferences (4-7 exchanges), then synthesizes positive prompt, negative prompt, recommended settings table, and pipeline…