SDXL 4 Step (FP32 with Improved UNET)
Note I used the 32bit CLIP-G
Refiner used in workflow also 32bit GGUF
Updated CLIP-L
For 4 Step use at CFG 1.0 - Load a image for workflow
For NSFW images the refiner should not be used
BRSGAN 2x can be found on Google Drive
2GB GGUF from FP32
Note 2GB requires separate clip and GGUF support, 4GB FP8 is ready to use in any SD GUI
Refined with baked FP32 Lora's
Quantized from the FP32 SDXL model for less loss
4GB SDXL (Full Checkpoint)
Custom CLIP is not Quantized
Custom UNET quantized to FP8 allowing for a balance of size and quality
Works in FORGE, Comfy-UI and Auto-1111
Works with LORA's
Beta/Deis is a good choice for img 2 img up-scaling
Both models have improved anatomy (Uncensored) for females however GGUF version does not do well with males.
Description
FAQ
Comments (9)
what base model this built on ?
The GGUF is a based of of FP32 SDXL with baked in FP32 lora's - The FP8 version is based of FP16 with FP8 Loras baked in
@Felldude ... which SDXL version this gguf built on ? vanilla or other trained one ?
@amazingbeauty How do you define trained, it has baked lora's but it was not finetuned. Its the base FP32 SDXL merged with FP32 Lora's to refine the UNET
@Felldude ok thank you
now cherry on top would be 4 step lightning lora merged in it to make it even faster please
😮
результаты действительно впечатляют, но в сравнению с другими xl моделями меньше хороших результатов, жду с нетерпением новых улучшенных версий модели
Спасибо, но для справедливости вам придется сравнить его с моделями на 2 ГБ или 4 ГБ. Возможно, когда-нибудь я смогу полностью настроить XL на FP32.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.









