Flux 2 Klein 9B_txt2img - LM Studio Prompt Enhancer - qwen3-coder-next | Sweet Tea Studio
WorkflowVerifiedExternal
Flux 2 Klein 9B_txt2img - LM Studio Prompt Enhancer - qwen3-coder-next
This workflow requires my Comfyui-lmstudio-prompt-enhancer custom node which is installable via Comfy Manager. Learn more about this custom node π IMPORTANT!!! You will need to search for, download, and load the model qwen3-coder-next in LM studio. You will also need to start the API server and generate an API Key. Learn how to configure LM Studio here. Notes for using qwen3-coder-next: This...
TaskText to imageFamilyFluxPublisherPuppet VisionUpdatedJul 11Bgrade
Runtime profile
Access
External workflow
Review
Verified
Publisher
Puppet Vision
Version
v1.0
Source
Civitai
Updated
Jul 11, 2026
Source description
This workflow requires my Comfyui-lmstudio-prompt-enhancer custom node which is installable via Comfy Manager.
Learn more about this custom node
π IMPORTANT!!!
You will need to search for, download, and load the model qwen3-coder-next in LM studio. You will also need to start the API server and generate an API Key. Learn how to configure LM Studio here.
Notes for using qwen3-coder-next:
This model is 80B (requires high memory) and it is fairly fast.
Although it's purpose is coding I included created a civitai workflow for this model as it won me first place in a civitai.com daily challenge.
If the workflow appears to hang on the LM Studio Prompt Enhancer node, donβt worry this is expected.
I set max tokens to 520, the max token length for Flux 2 prompts is 512, you can lower it if you don't want the LLM to ramble.
This workflow requires my Comfyui-lmstudio-prompt-enhancer custom node which is installable via Comfy Manager. Learn more about this custom node π IMPORTANT!!! You will need to search for, download, and load the model qwen3-coder-next in LM studio. You willβ¦
This workflow requires my Comfyui-lmstudio-prompt-enhancer custom node which is installable via Comfy Manager.
Learn more about this custom node
π IMPORTANT!!!
You will need to search for, download, and load the model qwen3-coder-next in LM studio. Youβ¦