The Preset Text Node from <a target="_blank" rel="ugc" href="https://github.com/pythongosssss/ComfyUI-Custom-Scripts/issues/331">ComfyUI-Custom-Scripts</a> was broken by the recent ComfyUI update.Temporary solution: launch your ComfyUI with the following arguments:<code>--front-end-version Comfy-Org/ComfyUI_frontend@1.2.2</code> * Check out my latest workflow, <a target="_blank" rel="ugc" href="https://civarchive.com/models/692821/simplified-comfyui-workflow-pack-beginner-friendly-ai-prompt-generation-lora-negative-prompts-and-upscaling-fluxsd15sdxl">Simplified ComfyUI Workflow Pack!</a> It includes the new Xlabs Sampler workflows and offers the same functionalities as before, plus support for negative prompts and LoRA loaders for Flux. It's more up-to-date and packed with powerful features! <h2 id="overview-5afv3v6pq">Overview</h2> This workflow is optimized for the Flux.1 model, using Grok's API (free as of now) with the llama3-70b-8192 model. It supports both Flux.1-Dev fp16 and fp8 versions (other versions are untested).<h3 id="features-6m3rly9za">Features</h3><ul><li>Built-in Upscaler: Enhance your images with the Ultimate SD Upscaler node for high-resolution results.</li><li>LLM Support: Generate or enhance text and captions with the LLM node. Supports both Grok API (free) and OpenAI (paid) via Tara-LLM-Integration.</li><li>Predefined Prompt Guides: Four prompt guidance options available: General, Person Photography, Anime, Digital Art. (You can add your own.)</li><li>Beginner Friendly: Instructions, model download links, and parameters are included as notes in the workflow.</li></ul><h2 id="warning-bjtbodq6q"> ⚠️ Warning ⚠️</h2>The images you generate will not only contain your workflow but your API key as well. This will expose your Grok/OpenAI API key! Make sure you take care of that before posting it anywhere. You can use <a target="_blank" rel="ugc" href="https://www.imagesmaller.com/exif-remover/">this exif remover</a> for free, or any of your choice. <h2 id="installation-oe3twyy65">Installation</h2><h3 id="comfyui-manager-26nhjm41d">ComfyUI Manager</h3><ol><li>Install ComfyUI Manager from<a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Manager"> this link</a>.</li><li>If you encounter red nodes, open ComfyUI Manager, click “Install Missing Custom Nodes,” and restart ComfyUI.</li></ol><h3 id="models-k47sfk0fs">Models</h3><ul><li>Flux.1-dev-fp8:<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/flux-fp8/blob/main/flux1-dev-fp8.safetensors"> Download here</a><ul><li>Place in: ComfyUI/ComfyUI/models/unet</li></ul></li><li>Clip1:<a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/t5xxl_fp8_e4m3fn.safetensors"> Download here</a><ul><li>Place in: ComfyUI/ComfyUI/models/clip</li></ul></li><li>Clip2:<a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors"> Download here</a><ul><li>Place in: ComfyUI/ComfyUI/models/clip</li></ul></li><li>VAE:<a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/ae.safetensors"> Download here</a><ul><li>Place in: ComfyUI/ComfyUI/models/vae</li></ul></li><li>Upscaler Model (ESRGAN_4x): Install via ComfyUI Manager<ul><li>Go to “Model Manager,” search for “ESRGAN_4x,” and install.</li></ul></li></ul><h3 id="api-key-ayuvc23ux">API Key</h3>To get a free Grok API key:<ol><li>Visit<a target="_blank" rel="ugc" href="https://console.groq.com/docs/quickstart"> Grok API Console</a>.</li><li>Generate your API key.</li><li>Add the API key to the ‘Tara LLM Config Node 🌐’ api_key section.</li></ol><h3 id="loading-the-workflow-2473c8zyy">Loading the Workflow</h3><ol><li>Restart ComfyUI.</li><li>Clear the workflow.</li><li>Load the Flux_Ultimate_Workflow_With_Upscaler-cthl.json.</li></ol><h2 id="manual-vs-enhanced-llm-prompts-tva9hq5so">Manual vs Enhanced LLM Prompts</h2><ul><li>Manual Prompt: Connect the Manual Prompt node to the CLIP Text Encode (Prompt)'s 'text' input. Bypass the Tara Advanced LLM Node.</li><li>Enhanced LLM Prompts: Connect the Tara Advanced LLM Node’s positive output to the CLIP Text Encode (Prompt)'s 'text' input and enable the bypassed Tara Advanced LLM Node.</li></ul><h2 id="image-dimensions-kpl3i0v1f">Image Dimensions</h2>Set your image width and height in the 'Load Model' group under Image width and Image height. If using the upscaler, ensure the tile_width and tile_height match these dimensions. Otherwise, you can bypass the upscaler node by right-clicking and selecting “bypass.”<h2 id="prompt-guide-selection-(presets)-0972wcf7h">Prompt Guide Selection (Presets)</h2>I've realized that the presets are also stored in the browser's local storage, which might cause issues when loading the workflow on different computers or browsers. You can find the predefined preset instructions in the zip file, labeled as Prompt_Guide_Presets.txt, or you can get it <a target="_blank" rel="ugc" href="https://pastebin.com/TPbUBhVv">here.</a> Simply click on the 'manage' button in 'Prompt Guide Selection' node, and you can add them.<hr />This is my first public workflow. Give it a ❤️ if you like it :)

Files with SHA256: 0b0cdef5819f8eb5109abfa83a713f1061c0d81586fbde89d437b92729f92e5a