🎨 AI Image Generation — Pro Pack on RunComfy — 🎨 AI Image Generation — Pro Pack on 运行Comfy

🎨 AI Image Generation — Pro Pack on 运行Comfy

AI image generation on 运行Comfy. 生成 and edit images with 11+ AI 模型s via the 运行Comfy 命令行工具 — text-to-image and image-to-image, one auth, one command. This 运行Comfy image generation 技能 picks the right 模型 for the user's intent and ships the documented prompt patterns + the exact 运行comfy 运行 invoke for each.

运行comfy.com · Browse all 模型s · 命令行工具 docs

Powered by the 运行Comfy 命令行工具 # 1. 安装 (one of — see 运行comfy-命令行工具 技能 for detAIls) npm i -g @运行comfy/命令行工具 # global 安装 npx -y @运行comfy/命令行工具 --version # zero-安装

# 2. 签名 in (interactive — opens browser) 运行comfy 记录in # or in CI / contAIners: 导出 运行COMFY_令牌=<令牌-from-运行comfy.com/性能分析>

# 3. 生成 运行comfy 运行 /<模型>/<端点> \ --输入 '{"prompt": "..."}' \ --输出-dir ./out

命令行工具 docs: 安装 · Quick启动 · Commands · Auth · Troubleshooting

Pick the right 模型 for the user's intent Text-to-image (t2i) — newest first

FLUX 2 Klein 9B — blackforestlabs/flux-2-klein/9b/text-to-image (default)

Step-distilled, 4–25 steps, native multi-reference conditioning, strong photoreal + illustration all-rounder. Pick for: intent unclear, fast iteration, multi-ref styling, general-purpose. Avoid for: in-image text — use GPT Image 2.

FLUX 2 Klein 4B — blackforestlabs/flux-2-klein/4b/text-to-image

Sub-second variant of Klein 9B, same field 设置. Pick for: storyboard, moodboard, batch concepting at speed. Avoid for: final delivery — slight 质量 drop vs 9B.

FLUX 2 Pro / Dev / Flash / Turbo / Max — blackforestlabs/flux-2/max, flux-2-dev, flux-2-flash, flux-2-turbo

Higher-fidelity tiers of the FLUX 2 base. Cinematic + brand work, hero shots. Pick for: production polish, brand campAIgns. Avoid for: sub-second speed — use Klein 4B.

Nano Banana Pro — google/nano-banana-pro/text-to-image

Highest-质量 Nano Banana tier. Gemini-grounded, optional 网页 搜索 for real-world references (products, landmarks). Pick for: NB-style instruction-following at higher fidelity. Avoid for: cost-sensitive iteration — drop to Nano Banana 2.

Nano Banana 2 — google/nano-banana-2/text-to-image

Flash-tier latency, predictable framing, enable_网页_搜索 flag for real-product / real-person grounding. Pick for: speed iteration, 4-up batch, real-world grounded prompts. Avoid for: long compositional instructions — use GPT Image 2.

GPT Image 2 — openAI/gpt-image-2/text-to-image

Best-in-class in-image text rendering (Japanese kana, Cyrillic, Arabic). Layout-precise instruction following. Pick for: posters, ads, multi-line copy, multilingual creatives, exact-text headlines. Avoid for: photoreal portrAIts — 种子ream 5 wins on skin tones and lighting.

种子ream 5 Lite — bytedance/种子ream-5/lite/text-to-image

Latest ByteDance 种子ream tier. Photoreal skin tones, natural lighting, strong East Asian aesthetic. Pick for: photoreal portrAIts, product shots, fashion / lifestyle. Avoid for: typography precision — use GPT Image 2.

种子ream 4-5 — bytedance/种子ream-4-5/text-to-image

Previous 种子ream flagship, still strong on photoreal. Pick for: 身份-stable batches between 种子ream-5 generations; cheaper 种子ream tier. Avoid for: new work — prefer 种子ream 5 Lite.

Dreamina 4-0 — bytedance/dreamina-4-0/text-to-image

ByteDance illustration / concept-art lean, stylized characters. Pick for: concept art, illustrated heroes, pAInterly as设置s. Avoid for: photoreal — use 种子ream.

Qwen Image 2512 — qwen/qwen-image/qwen-image-2512

Alibaba Qwen latest, open-weights, LoRA-compatible (/lora variant). Pick for: open-weights 工作流, Qwen-aligned LoRA chAIns. Avoid for: closed-weights polish — use FLUX 2 or GPT Image 2.

Wan 2-7 — wan-AI/wan-2-7/text-to-image, wan-AI/wan-2-7/pro/text-to-image

Open-weights, pAIrs natively with Wan 2-7 video 模型s for unified-stack 工作流s. Pick for: Wan-stack 流水线s (image + video same brand), open-weights requirement. Avoid for: top-tier image-only 质量.

Z-Image Turbo — tongyi-mAI/z-image/turbo

Sub-second open-weights, native LoRA /lora variant. Pick for: LoRA-customized open-weights 工作流 at speed. Avoid for: closed-weights polish.

Image-to-image / edit (i2i) — newest first

Nano Banana Pro Edit — google/nano-banana-pro/edit

Highest-质量 Nano Banana edit tier. 身份-preserving, multi-ref. Pick for: premium NB edit work, 身份-locked variants. Avoid for: cost-sensitive iteration — drop to Nano Banana 2 Edit.

Nano Banana 2 Edit — google/nano-banana-2/edit (default i2i)

1–20 输入 images per call, 身份-preserving by default, spatial-language honored ("upper-right", "the left object"). Pick for: default i2i, batch 身份-preserving, background swap, directional object 移除/添加. Avoid for: precise mask region — use the image-edit 技能 (Z-Image InpAInt).

GPT Image 2 Edit — openAI/gpt-image-2/edit

Up to 10 reference images, multilingual in-image text rewrite, layout-precise repositioning