Model Information






Description
FULLY_REAL_XL - F.U. Edition
F.U. Edition = FLUXed Up edition. I did not want to use FLUX in the title because this is an SDXL model not FLUX. So how is it related, this checkpoint took my most popular model and trained it on images from the incredible new FLUX model. This has pushed the model to all new levels of detail. V1 was proof of concept. V2 is putting the concept into action with training on 6000 new images over MANY hours.
We are seeing the next generation of models and they are amazing. Much like SD1.5 the past year, SDXL still has a role to play while the next generation of models become optimized. It is a great option for the 1000's of existing resources and for those who lack the computing power the newer models currently demand.
FULLY_REAL_XL is BACK!!!
I have had this model pulled from circulation for months now - but now it is back! If you like it, download it while you can. This was based on the FULLY_REAL_XL models. I am changing it over to the FU editions moving forward.
Recommended Settings:
CFG 3-6 (I use 4 mainly.)
40-60 steps = this is not an accelerated version
You can use a lot of samplers. I normally use DPM++ 2M SDE Karras or DPM++ 3M SDE Expo.
Disclaimer: This model is provided for educational purposes and for the advancement of AI art in general. The creator of this checkpoint assumes no responsibility or liability for the end user's outputs. Any illegal, unethical, or deep fake use of this model is the sole responsibility of the user engaged in those activities. The end user assumes all liabilities from use of the checkpoint.
No permissions are given for anyone to distribute this model on other sites. I do not give permission for it to be used on any image generation service other than CIVITAI.
Side note about releasing this model:
I still have many of the same concerns that drove me to remove this checkpoint series from circulation. I also still have issues with how CIVITAI selects models for onsite generation. However, I think FLUX and SD3 will draw most of the legal scrutiny moving forward because their current and potential results will soon overshadow these models. I am your typical temperamental type though so get it before I change my mind again. (At least I am honest...)
FULLY_REAL_XL
v1 F.U. Edition
Model Details
- Type
- AI Model
- Task
- text-to-image
- Subtype
- Safetensors / Checkpoint AI Model
- Created
- Updated
- June 7, 2026