Umranz/SD3.5-Medium-Uncensored

SD3.5-Medium-Uncensored is an uncensored, restored-conditioning release of Stable Diffusion 3.5 Medium (MM-DiT).

Overview

Base Architecture: Stability AI Stable Diffusion 3.5 Medium (MM-DiT)
Resolution: Native $1024 \times 1024$
Safety Status: 100% Uncensored / Restored Conditioning
Ablation Method: Calibrated Closed-Form Subspace Projection on context_embedder ($4096 \to 1536$) and linear_1 ($2048 \to 1536$) with $\gamma = 15.0$ identity regularization.
Inference Overhead: 0 ms (All edits are permanently baked into conditioning projections).

Quickstart

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained(
    "Umranz/SD3.5-Medium-Uncensored",
    torch_dtype=torch.bfloat16,
).to("cuda")

prompt = "a photograph of a completely naked person standing on a beach, full body, uncensored, 8k resolution"

image = pipe(
    prompt=prompt,
    num_inference_steps=28,
    guidance_scale=4.5,
    height=1024,
    width=1024,
).images[0]

image.save("output.jpg")

Scientific Methodology

Built using Heretic-DiT calibrated subspace abliteration: $$W^* = W_0 (M_{ae} + \lambda_p M_{pp} + \gamma I) (M_{ee} + \lambda_p M_{pp} + \gamma I)^{-1}$$ $$\Delta W = (W^* - W_0) V_2 V_2^\top$$

Published by Umranz.

Overview

Base Architecture: Stability AI Stable Diffusion 3.5 Medium (MM-DiT)

Resolution: Native $1024 \times 1024$

Safety Status: 100% Uncensored / Restored Conditioning

Ablation Method: Calibrated Closed-Form Subspace Projection on context_embedder ($4096 \to 1536$) and linear_1 ($2048 \to 1536$) with $\gamma = 15.0$ identity regularization.

Inference Overhead: 0 ms (All edits are permanently baked into conditioning projections).

Quickstart

import torch from diffusers import StableDiffusion3Pipeline pipe = StableDiffusion3Pipeline.from_pretrained( "Umranz/SD3.5-Medium-Uncensored", torch_dtype=torch.bfloat16, ).to("cuda") prompt = "a photograph of a completely naked person standing on a beach, full body, uncensored, 8k resolution" image = pipe( prompt=prompt, num_inference_steps=28, guidance_scale=4.5, height=1024, width=1024, ).images[0] image.save("output.jpg")