LLM Writer – Krea2 & Illustrious (LM Studio)
Turn a short idea, or up to 8 reference images, into a ready-to-use prompt with a local LLM running in LM Studio, then generate with Krea2 or Illustrious from the same workflow.
FEATURES
• One switch for Krea2 / Illustrious: the unused branch is muted, and the LLM writes natural language for Krea2 or Danbooru-style tags for Illustrious.
• Up to 8 reference images, each with toggles for what to take from it: Action, Pose, Person, Clothing, Background, Style, Camera / POV. Only the enabled aspects are used.
• Images are described automatically before generating. You can also describe them one by one.
• Output style, number of people (1–8, Auto or Custom) and camera framing selectors.
• ✏️ Modify: ask for a small change (e.g. "make the hair red") and the LLM edits only that.
• LoRA trigger words from Lora Manager are inserted automatically.
• Negative embeddings picker for Illustrious.
• Optional Spanish view of the prompt, editable and translated back to English before generating.
• Base image i2i with denoise for both branches. Leave it empty for text to image.
• Size node with aspect ratio + megapixels and a live pixel preview.
• Save Image node with an auto save on/off switch and a manual 💾 Save button.
• The model is unloaded from LM Studio after generating (optional), freeing VRAM for the image model.
REQUIRED CUSTOM NODES
• LD PromptWriter (LM Studio) – search "LD PromptWriter" in ComfyUI Manager, or https://github.com/damidero/ComfyUI-LD-PromptWriter-LMStudio
• ComfyUI-Lora-Manager – https://github.com/willmiao/ComfyUI-Lora-Manager
• ComfyUI-Custom-Scripts (PlaySound, optional) – https://github.com/pythongosssss/ComfyUI-Custom-Scripts
MODELS
• Krea2 UNET: Krea2-Turbo-HD-V1-int8_convrot – https://huggingface.co/wikeeyang/Krea2-Turbo-HD-V1
• Krea2 CLIP qwen3vl_4b_fp8_scaled + VAE qwen_image_vae – https://huggingface.co/Comfy-Org/Krea-2
• Illustrious: WAI Illustrious SDXL v17 – https://civitai.com/models/827184/wai-illustrious-sdxl
(or Illustrious Realism – https://civitai.com/models/2354628/illustrious-realism)
• LLM: Qwen3-VL 8B Instruct in LM Studio (vision needed for images) – https://lmstudio.ai/models/qwen/qwen3-vl-8b
HOW TO USE
1. Open LM Studio, start the local server and load a vision model.
2. Set the server URL in the LM Studio Config node and pick Krea2 or Illustrious.
3. Write an idea and/or load reference images, and choose what to take from each one.
4. Press ✍️ Generate prompt, check the text and queue the workflow.
TIPS
• If the positive box already has text, the workflow uses it as is and does not call the LLM. Clear it to generate a new one.
• If the model "thinks" and returns no prompt, turn off Reasoning / Thinking in LM Studio.
• Krea2 LoRAs don't work with Illustrious and vice versa. Swap them when you change engines.

