This Comfyui workflow is batch generating preview images for loras (i.e character lora ID-Photos).
In batch advances through all (or folder/category) your Loras
Generate prompt from Lora filename, trigger word (from Civitai) and your custom text
Generate image with text overlay of filename and trigger word from Civitai
Saves image with Lora filename
Things you need to adjust:
Select Path / Start Lora
Select your main checkpoint
Select secondary lora (here i use DMD2 for speed.)
Adjust the Replace node "MeineLoras\" if you use folders or categories. This part is stripped from the lora filename/path.
Adjust your prompt and latent resolution.
Workflow as json and embedded in preview png.
Description
FAQ
Comments (1)
Thanks for sharing this great workflow — it's very helpful. I've been looking for a way to compare outputs of different LoRAs using the same prompt.
If anyone has LoRAs stored in subfolders, you might run into an issue where the image can't be saved because some parts of the output path are not created automatically. This happens because the Save node receives not the full output path, but only a prefix.
I had to modify the was_node-suite.py in the custom_nodes/was-ns folder at line 7488:
After:
Add this:
os.makedirs(os.path.dirname(output_file), exist_ok=True)Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.