Black Mixture
patreon
🧧 Black Mixture’s Flux UNO (Reference-Guided Image Generation for Product Mockups & More)
🕑 Added 2025-04-17 20:45:01 +0000 UTCHey Black Mixture Fam! 👋🏾 We’re back with another 🔥 ComfyUI workflow, this time featuring the Flux UNO model, a powerful new method for reference-based image generation!
This new model is perfect for product mockups, consistent character design, outfits, and object-specific scenes! This workflow brings your ideas to life using an image reference as guidance without LoRAs to train or elaborate prompt tweaking. Just clean, guided generations based on your input image.
*** Works well for generating images to animate using Wan 2.1! Get the advanced Wan 2.1 image to video workflow here: https://www.patreon.com/posts/black-mixtures-1-124117186
📥 Model & Node Setup
Required Files & Installation
Place these files in the correct folders inside your ComfyUI directory:
🔹 UNO Custom Node
Clone directly into your custom_nodes folder:
📂 ComfyUI/custom_nodes/ComfyUI-UNO
Or manually download and unzip the ComfyUI-UNO.zip file linked at the bottom of this post.
🔹 UNO Lora File
Download uno_lora.safetensors from this post
or
🔗 https://huggingface.co/bytedance-research/UNO/tree/main
📂 Place in: ComfyUI/models/loras
🔹 Flux1-dev-fp8-e4m3fn.safetensors Diffusion Model
🔗 https://huggingface.co/Kijai/flux-fp8/tree/main
📂 Place in: ComfyUI/models/diffusion_models
🔹 VAE Model
🔗https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/ae.safetensors
📂 Place in: ComfyUI/models/vae
IMPORTANT! Make sure to use the Flux1-dev-fp8-e4m3fn.safetensors model.
✨ Features
Generate highly accurate images using a reference
Perfect for product photography, mockups, clothing consistency
Great for stylized AND realistic image outputs
Side-by-side comparison output option included
Clean, minimal UI flow with optional addons
🎨 Workflow Sections
Color-coded for clarity:
🟥 Load Image + Models
🟨 Prompt + Generation Settings
🟩 Review Generation Results
🟪 Important Notes
⚙️ Quick Start Guide
Update ComfyUI to the latest version
Install the ComfyUI-UNO node
Download and place the uno_lora.safetensors file
Load our Flux UNO workflow
Drag in a reference image + enter your prompt
Click generate and review results!
💡 Important Notes
The reference image is used as a strong guidance — results are inspired by the image, not copied
Works especially well for fashion, objects, and logos
Pick Your Addons node gives a side-by-side comparison if you need it
Settings are optimized but feel free to adjust CFG and steps based on speed and results.
📸 We’ve included example generations in this post so you can see the magic in action!
Check out the video tutorial: https://youtu.be/eMZp6KVbn-8
Created by Nate Dwarika from The Black Mixture Team
💝 THANK YOU to all our amazing Patrons for supporting these releases!
Comments
Black Mixture
Hi Wyatt, are you using Runpod with a persistent storage? This error can happen when a model file is corrupted. Besides the UNO lora and Flux Dev, the node will download the text encoders in the background. You might want to double check that these downloaded correcrly as well.
Wyatt Holl
hi thank you for creating and sharing this, I keep getting the following error when trying to run this: UNOModelLoader Error while deserializing header: HeaderTooLarge I tried downloading the uno_lora multiple ways and I believe the file isnt corrupt, so Im not sure what is happening I also tried different runpods and everything
Black Mixture
Hi Ben, happy to help with this! Can you try clicking into your CMD window and pressing ENTER on your keyboard and see if it updates? It looks like it is getting stuck loading the model files. Sometimes, this can happen when Windows "defocuses" the process and pressing ENTER while clicking in the CMD can help re focus it. Also you can try to run this workflow without having other programs running in the background if your computer is running out of memory. If you're still having issues, you can try sending a screenshot to the priority-support channel on Discord. Just link your Patreon and Discord account and you should get access and a special role which will allow you to visit the priority-support channel. Sometimes, screenshots can help me troubleshoot issues better.
Ben Kwok
Thanks for sharing the workflow! I entered an error. I got all the models downloaded to the specified directory, and when I ran the workflow, they all seem loaded well. But the running progress just stop there. When I checked the CMD window, here is the last line: Fetching 2 files: 0%| | 0/2 [00:00
Black Mixture
Hi Loughlin, this error can happen either when the model files are corrupted or when using an incorrect model. You can try redownloading the model files and that might help. I'd recommend trying the smaller files first like the ae.safetensors file to see if the issue is there before trying the larger text encoder and Flux model.
loughlin john
hey thanks for this, I'm getting error: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device. any advice? cheers
Z 2
Man, this is actually pretty amazing ! Cheers !
