Model Information
%20(Full%20model%20%26%20LoRA%20version).jpeg&w=1920&q=75)
%20(Full%20model%20%26%20LoRA%20version).jpeg&w=1920&q=75)
%20(Full%20model%20%26%20LoRA%20version).jpeg&w=1920&q=75)
%20(Full%20model%20%26%20LoRA%20version).jpeg&w=1920&q=75)
%20(Full%20model%20%26%20LoRA%20version).jpeg&w=1920&q=75)
%20(Full%20model%20%26%20LoRA%20version).jpeg&w=1920&q=75)
Description
Experimental merge of SD3.5 Large and Turbo. I saved when I found a good balance at 8 steps, but needs further testing! So far, quality seems better than Turbo model with little speed sacrifice, although it can make some pretty incoherent images too.
Good results with CFG 1.0-3.0
Work in progress
Merge x, y embedder and half the blocks from SD3.5 Large Turbo into SD3.5 Large, and context embedder, pos embed at 0.3 ratio.
PS. I borrowed some test prompts from SD3.5 image feed :)
Comparisons


























SD 3.5 Fusion (8 steps merge) (Full model & LoRA version)
753downloads
Download ModelModel Details
- Type
- AI Model
- Task
- text-to-image
- Subtype
- Safetensors / Checkpoint AI Model
- Created
- Updated
- June 8, 2026