Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This is a very simple workflow that helps you to save your SDXL Text to Image Generation Data into a human readable .txt file. This will automatically get and write your metadata to the .txt file. You will find all...
Runtime profile
Source description
This is a very simple workflow that helps you to save your SDXL Text to Image Generation Data into a human readable .txt file. This will automatically get and write your metadata to the .txt file. You will find all the saved prompt files that it generated with the images inside the Archive (.Zip) that has the workflow. Also with the Image Saver Simple node used you may embed the workflow itself with each saved image or save the image and workflow for your work separately. In this way a readable .txt file for each run of this workflow will be generated (matching Automatic1111 / EasyDiffusion's .txt outputs).
As you can see from the screenshot of the output format this is very much readable and ideal for easy reference reuse if you want to reuse the prompt on a different tool like WebUI Forge or Easy Diffusion or something else. This saves both the weights of LORAs along with one or multiple positive & negative embedding(s) with the prompt. For SDXL 1.0 (or SD 1.5 or any other models based on SD 1.5 / SDXL 1.0) having at least one positive embedding and one negative embedding is crucial to have quality output, you may not wanna skip them, this workflow makes it easier to neatly manage and track usage of both embeddings and LORAs. I have provided a more detailed lists of all the LORAs and embeddings for all different kinds of generation examples I have given inside the Archive (.Zip) that has the workflow; look for "Prompt_Helpers_List.txt".
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This SDXL 1.0 ComfyUI workflow is for text-to-image generation and readable run records. It takes an SDXL model, positive and negative embeddings, image dimensions, a prompt, image count, sampler, CFG, steps, and optional LoRAs, and produces generated images with a readable .txtم
Choose the model and embeddings, set image dimensions, enter a prompt, select image count and sampling settings, then run the workflow.
Each .txt record includes the prompt, LoRA weights, and positive and negative embeddings used for the run.
Saved images can include the workflow, or the images and workflow can be saved separately.
The readable text format follows the style of Automatic1111 and Easy Diffusion outputs and supports prompt reuse in WebUI Forge or Easy Diffusion.
Use a sufficiently current ComfyUI installation, install the needed nodes with ComfyUI Manager, and place the model, LoRAs, and embeddings in their expected locations.
The listed SDXL 1.0 AIO model is RealVisXL V3 (BAKED VAE); Prompt_Helpers_List.txt contains download links for the listed LoRAs and embeddings.
Required ComfyUI node packs include ComfyUI-Simple_Readable_Metadata-SG, ComfyUI-Custom-Scripts, and ComfyUI-Easy-Use.
Also required are ComfyUI-Image-Saver, ComfyUI-Lora-Manager, and ComfyUI-KJNodes.
Other required node packs are ComfyUI_JPS-Nodes, comfy-image-saver, and Comfyui-Memory_Cleanup.
Set image dimensions, image count, sampler, CFG, and steps before running.
LoRA use is optional; add LoRAs through LORA Manager, and load positive or negative embeddings by name after installing them in the correct path.
With matching model, encoder, VAE, LoRAs, and embeddings, you can repurpose the workflow for SD 1.5, Pony, or Illustrious with minimal modification.
If you use v1-5-pruned-emaonly-fp16.safetensors, verify that it matches the Comfy-Org/stable-diffusion-v1-5-archive source and its listed hash before use.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
2 excerptsSource context: 221 downloads · Type Workflows · Base model SDXL 1.0
Note that with proper selection of matching files (model + encoder + VAE or an AIO model, properly matched LORAs & positive/negative embeddings) you can repurpose this workflow for SD 1.5, Pony & Illustrious too.. just as it is or performing very minimal modification.
You can download your necessary SDXL 1.0 AIO model (with baked in text encoder & VAE), LORAs & embeddings used from CivitAI (Details are mentioned below). Make sure you have latest enough ComfyUI installation and install any necessary nodes for for this workflow using ComfyUI manager and download and place correct files (SDXL 1.0 AIO model, LORAs, embeddings etc) in correct places using the LORA Manager (yes! the LORA Manager is simply not just for LORA management, it can also handle Model files and embeddings too). Also check out my other workflows for SD 1.5 + SDXL 1.0, Pony, WAN 2.1, WAN 2.2, MagicWAN Image v2, QWEN, HunyuanImage-2.1, HiDream, KREA, Chroma, AuraFlow, NoobAI, Illustrious, Lumina2, Z-Image Turbo, Flux.2 Klein (4B & 9B), Flux.1 Dev and Kandinsky Image 5 Lite (T2I & I2I) models. Feel free to toss some yellow Buzz on stuffs you like.
How to use this -
#1. Just select your desired SDXL 1.0 AIO model and embeddings first and now
#2. set your desired image dimensions to start
#3. then input your desired image prompt.
#4. select how many images you want (Change the number besides the "Run" button)
#5. select image sampling methods, CFG, steps etc. settings
#6. finally press the run button to generate. That's it..
** LORA usage for this workflow is optional you can use it without any LORAs, use with 1 or 2 or any other number of LORAs. to add new LORAs press the L button on top to lunch LORA Manager on a new tab find your LORA and if you want to use that LORA just click the upward Kite button. For many Pony models it is vital to select that model's recommended positive & negative embeddings but can of course disable or bypass these. Same thing can be said for your usage of positive or negative embeddings using "Load Embeddings by Name" nodes, on these if you start typing the name of your desired embedding (once installed in correct path) it will automatically try to locate and link the correct one to your positive/negative prompt. You don't need to disorganizedly and incorrectly put them inside the positive/negative prompt itself.
Required Files
===============
RealVisXL V3 (BAKED VAE) -
**I deliberately used V3 because this one has the most useful matching v3 Inpainting model also with baked VAE. This allows seamless, fast & good quality inpainting tasks.
Inside the Archive (.Zip) that has the workflow; look for "Prompt_Helpers_List.txt". This will have a detailed long list of download links for all LORAs & Embeddings used with clear reference to in which example image(s) they are used.
Estimated VRAM requirement
6 GB estimated
1.99 GB of model files. Model file total + 25% loading overhead + 2 GB execution buffer, rounded up.
Requirements
10 requirementsCheckpoint · 1.99 GB · Hugging Face · Comfy-Org/stable-diffusion-v1-5-archive
Node pack · Registry
Node pack · Registry
Source context: 190 downloads · Type Workflows · Base model SDXL 1.0
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
