!!! Before installing custom nodes from manager you need to install this one from Git url<a target="_blank" rel="ugc" href="https://github.com/BigStationW/ComfyUI-ppm">https://github.com/BigStationW/ComfyUI-ppm</a> - negative prompts for Flux1, ZIT and Anima For example if you don't want to see glasses and tie on Anima, Zit and Flux1 generations add to fixed prompt window string (glasses, tie:-1)If manager fails to find LLM and lora nodes, install them from git url - <a target="_blank" rel="ugc" href="https://github.com/willmiao/ComfyUI-Lora-Manager">https://github.com/willmiao/ComfyUI-Lora-Manager</a><a target="_blank" rel="ugc" href="https://github.com/KingManiya/ComfyUI-LLM-text-processor">https://github.com/KingManiya/ComfyUI-LLM-text-processor </a>(Automatic setup currently supports Windows x64 CUDA 13 only. Other platforms require manual setup of llama.cpp release binaries.)Workflow can be used with Sage Attention enabled in Comfyui launch arguments (it can be easily installed from <a target="_blank" rel="ugc" href="https://github.com/wildminder/AI-windows-whl?tab=readme-ov-file">https://github.com/wildminder/AI-windows-whl?tab=readme-ov-file</a> with no need to install compiler)This workflow support Nodes 2.0 and:<ul><li>Z-Image, Krea-2, Flux, Flux 2, Flux 2 Klein, Anima, Qwen Image, Qwen Image Edit, SDXL/Pony, txt2img, img2img, Inpaint functionality.</li><li>Face swap (not that perfect atm)</li><li>Krea-2 generation with image (or images) reference</li><li>Double sampling (switch under sampler)</li><li>LLM to describe images and enhance prompts</li><li>ControlNet only for Edit models in img2img group (just describe your image in prompt and add some instruction like "use input image as normal map reference")</li><li>Outpainting in Edit/Kontext mode</li><li>safetensor and gguf checkpoints and text encoders</li><li>AfterDetailer</li><li>Powerful multi Lora loader (Lora manager)</li><li>Multi or single images load for Edit/Kontext/Krea Reference</li></ul><h3 id="llm-models:">LLM Models:</h3>VRAM 8 Gb:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf">Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive/resolve/main/mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf">mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf</a></li></ul>VRAM 12+ Gb:<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive/resolve/main/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf">Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive/resolve/main/mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf">mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf</a></li></ul>or<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf">Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf">mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf</a></li></ul><h3 id="put-models-and-folder-with-system-prompt-here:">Put models and folder with system prompt here:</h3><pre><code>📂 ComfyUI/
├── 📂 models/
│ └── 📂 LLM/
│ ├── Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf
│ ├── mmproj-Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-f16.gguf
│ └── 📂 prompts/
│ ├── LLM-system.txt
│ ├── LLM-system-SDXL.txt</code></pre>Starting from v8.0, it is possible to enhance T2I prompts on the fly using switches in the T2I group. You still need to manually copy and paste prompts from the LLM group to the I2I group, but you can directly describe Image 1 loaded in the I2I block.Follow the short block notes for more information.User prompts in both groups are now divided into two parts. The first part (Fixed) is never passed to the LLM block for processing and will always remain unchanged at the beginning of the prompt. The second part (User Prompt) can be passed to the LLM (if enabled) and improved.

All-in-One. Z-Image, Krea2, Klein, t2i, i2i, controlNet, inpaint, outpaint, LLM, Qwen image, SDXL

<ul><li>Wan group replaced with Krea-2 + few optimizations (8.9)</li><li>Inpainting in Forge style can be disabled with zoom mask switch (8.8)</li><li>Minor changes in i2i preprocess logic (8.8)</li><li>Lens loader group (8.7)</li><li>Otpainting fix (8.6)</li><li>Inpainting in Forge/Automatic111 style (8.6)</li><li>Almost all custom nodes that haven’t been updated for more than 6 months have been removed from the workflow (8.4)</li><li>Separate version for Sage Attention (8.3)</li><li>Negative prompts for Anima, Flux1 and Zit (8.2)</li><li>LLM system prompt for SDXL format (8.2)</li><li>Universal LLM system prompt (8.1)</li><li>Clear VRAM on every Run if the LLM enabled (8.1)</li><li>New LLM node</li><li>General cleanup</li><li>Useful information and links inside workflow</li></ul>

Files with SHA256: 35230333b369c0df414f526f7c8f15b1e4a7fc317dad3bae5c8b6e86dfd4fefc