I'd like to share Fooocus-MRE (MoonRide Edition), my variant of the original Fooocus (developed by lllyasviel), new UI for SDXL models.
We all know SD web UI and ComfyUI - those are great tools for people who want to make a deep dive into details, customize workflows, use advanced extensions, and so on. But we were missing simple UI that would be easy to use for casual users, that are making first steps into generative art - that's why Fooocus was created. I played with it, and I really liked the idea - it's really simple and easy to use, even by kids.
But I also missed some basic features in it, which lllyasviel didn't want to be included in vanilla Fooocus - settings like steps, samplers, scheduler, and so on. That's why I decided to create Fooocus-MRE, and implement those essential features I've missed in the vanilla version. I want to stick to the same philosophy and keep it as simple as possible, just with few more options for a bit more advanced users, who know what they're doing.
For comfortable usage it's highly recommended to have at least 20 GB of free RAM, and GPU with at least 8 GB of VRAM.
You can find additional information about stuff like Control-LoRAs or included styles in Fooocus-MRE wiki.
List of features added into Fooocus-MRE, that are not available in original Fooocus:
Support for Image-2-Image mode.
Support for Control-LoRA: Canny Edge (guiding diffusion using edge detection on input, see Canny Edge description from SAI).
Support for Control-LoRA: Depth (guiding diffusion using depth information from input, see Depth description from SAI).
Support for Control-LoRA: Revision (prompting with images, see Revision description from SAI).
Adjustable text prompt strengths (useful in Revision mode).
Support for embeddings (use "embedding:embedding_name" syntax, ComfyUI style).
Customizable sampling parameters (sampler, scheduler, steps, base / refiner switch point, CFG, CLIP Skip).
Displaying full metadata for generated images in the UI.
Support for JPEG format.
Ability to save full metadata for generated images (as JSON or embedded in image, disabled by default).
Ability to load prompt information from JSON and image files (if saved with metadata).
Ability to change default values of UI settings (loaded from settings.json file - use settings-example.json as a template).
Ability to retain input files names (when using Image-2-Image mode).
Ability to generate multiple images using same seed (useful in Image-2-Image mode).
Ability to generate images forever (ported from SD web UI - right-click on Generate button to start or stop this mode).
Official list of SDXL resolutions (as defined in SDXL paper).
Compact resolution and style selection (thx to runew0lf for hints).
Support for custom resolutions list (loaded from resolutions.json - use resolutions-example.json as a template).
Support for custom resolutions - you can just type it now in Resolution field, like "1280x640".
Support for upscaling via Image-2-Image (see example in Wiki).
Support for custom styles (loaded from sdxl_styles folder on start).
Support for playing audio when generation is finished (ported from SD web UI - use notification.ogg or notification.mp3).
Starting generation via Ctrl-ENTER hotkey (ported from SD web UI).
Support for loading models from subfolders (ported from RuinedFooocus).
Support for authentication in --share mode (credentials loaded from auth.json - use auth-example.json as a template).
Support for wildcards (ported from RuinedFooocus - put them in wildcards folder, then try prompts like
__color__ sports carwith different seeds).Support for FreeU.
Limited support for non-SDXL models (no refiner, Control-LoRAs, Revision, inpainting, outpainting).
Style Iterator (iterates over selected style(s) combined with remaining styles - S1, S1 + S2, S1 + S3, S1 + S4, and so on; for comparing styles pick no initial style, and use same seed for all images).
If you find my work useful / helpful, please consider supporting it - even $1 would be nice :).
Description
Changes since v2.0.78.2:
Added Style Iterator,
Added limited support for non-SDXL models (no refiner, Control-LoRAs, Revision, inpainting, outpainting).
Removed meta tensor usage,
Added Load Last Prompt button (contribution from sngazm),
Fixed hangup in Upscale (Fast 2x),
Fixed problems with turning off FreeU in some scenarios,
Fixed loading prompts from JPG files processed by external apps,
Fixed fast upscale always saving as PNG,
Fixed loading TAESD decoder for SD from custom path.
FAQ
Comments (16)
fantastic job! Is there a way to set certain options by default? such as the option always being activated "Save Metadata in Image" etc
@Teufel_ Yup - via settings.json file. You can look at settings-example.json, and use it as a template. You don't have to use all the entries - using only those you want to change will work, too (settings-no-refiner.json is an example of that).
@MoonRide thank you so much! you're amazing
@Teufel_ Thank you for your kind words, but most of the credits should go to comfyanonymous (author of ComfyUI backend) and lllyasviel (author of the original Fooocus) - I am just slightly enhancing their work :).
The image quality and speed of this is really outstanding! I'm so impressed with the image output quality from this UI! And it has continued to get better and evolve over the past few months! It's REALLY an amazing gift to the generative AI community! THANK YOU for all your hard work!
I'll use this more and more since Automatic1111 and SD next generate awful images with my 1050Ti.
Very sad that the official Fooocus does not support 2.1 models, since they are technically more comparable to Midjourney than SDXL.
how do I make it so it doesn't save my outputs to a local file?
How do I make it so it doesn't download the sd_xl base and refiner after I delete them?
In the presets folder are json files for each run_.bat configuration. Blank out "checkpoint_downloads", "embeddings_downloads", "lora_downloads" to stop them from downloading again.
I downloaded it,but nothing happens? It doesn't work I updated the models I had from the original fooocus, but nothing to do so I deleted everything, to come back to original fooocus
After downloading full package and unzipping it you can just launch run-mre.bat. If you already have downloaded model files you can set it via paths.json. Many of MRE-specific changes are now available in the original Fooocus (see https://github.com/lllyasviel/Fooocus/discussions/689, and I also ported some other featuers aside of this discussion), so you can just stick to it, if it works fine for you.
Really good tool
Everybody comes out looking waxy and fake. Not sure if I'm doing something wrong or is it FMRE?
I don't know what happened, but the problem seems to have fixed itself?
@AntiBlondie I would need to get some more details to be able to diagnose the problem. If it happens again try figuring out reproduction path, step by step.
Please Update to Support RTX 50 Series Blackwell Architecture, I Try to Run But not responding, (Now I'm Using Fooocus for RTX 50 Series)