Based on good NSFW Lora/LoKr, I've experimented with reduced size/weight: dropping the DIT/UNET layer part because the model already know how to do NSFW. keeping only the text encoder/fusion layers from the NSFW lora.This technique can reduce Krea2 lora weight (reduce ANY lora/lokr weight)exemple with this lora 218mo =&gt; 13.5moexemple with LoKr 1.46go =&gt; 40mo or even 20mo in some caseI simply use the safetensors python lib and keep only the txtfusion.layerwise_blocks and txtfusion.refiner layers from NSFW lora. Dropping the other layers as the model know how to draw nsfw stuff ;).I wanted to experiment with the Krea2 model and understand two things:<ol><li>If the model was trainned on NSFW (I think it was or it couldn't draw NSFW without UNET/DIT layer part)</li><li>Where is the NSFW influence in the model: txtfusion.layerwise_blocks seems to have 80% of the NSFW decision making and txtfusion.refiner 20% ish. txtfusion.projector is a small vector and I think it should not be touched too much (it merge the 12 big vector from qwen3vl) but doesn't directly influence NSFW.</li></ol>Detail and code at the end.detail of the token handling before DIT as I think I understand it (maybe wrong):<pre><code>'''
 Frozen Qwen3-VL-4B (Text Encoder)
 (hidden dim ~2560)
 |
 | Select 12 specific layers
 | [2,5,8,11,14,17,20,23,26,29,32,35]
 v
 12 x (Seq_len, 2560) hidden states
 |
 | Stack / Concat along layer dim
 v
 [12, Seq_len, 2560] ← multilayer input
 |
 +---------------------------------------------------+
 | txtfusion.layerwise_blocks |
 | (2 blocks, cross-layer attn) |
 +---------------------------------------------------+
 |
 Block 0:
 - prenorm (RMSNorm scale [2560])
 - attn: wq/wk/wv/wo/gate [2560,2560] + qknorm
 - mlp: down[2560→6912] / gate[6912,2560] / up[6912,2560]
 - postnorm (RMSNorm scale [2560])
 |
 Block 1: (same structure as Block 0)
 |
 v
 Fused layer-wise features [Seq_len, 2560]
 |
 +---------------------------------------------------+
 | txtfusion.projector |
 | Linear(12 → 1) weight [1, 12] |
 +---------------------------------------------------+
 |
 v
 Single fused representation per token
 (or pooled/processed) [Seq_len, 2560]
 |
 +---------------------------------------------------+
 | txtfusion.refiner_blocks |
 | (2 bidirectional transformer blocks)|
 +---------------------------------------------------+
 |
 Refiner Block 0:
 - prenorm (RMSNorm [2560])
 - attn: wq/wk/wv/wo/gate [2560,2560] + qknorm
 - mlp: down/gate/up (same as above)
 - postnorm
 |
 Refiner Block 1: (identical structure)
 |
 v
 Refined bidirectional text features [Seq_len, 2560]
 |
 +---------------------------------------------------+
 | txtmlp |
 | (final text MLP / projection) |
 +---------------------------------------------------+
 |
 txtmlp.0.scale [2560] ← residual / scaling
 |
 txtmlp.1: Linear [2560 → 6144] + bias
 |
 txtmlp.3: Linear [6144 → 6144] + bias
 |
 v
 Final conditioned text embeddings
 (ready for cross-attention into DiT)
 |
 ↓
 Injected into first DiT / unet_blocks
 (via cross-attention in the main transformer)</code></pre>Code for the layer stripping:<pre><code>from safetensors import safe_open
from safetensors.torch import save_file
from pathlib import Path

def strip_layers(input_file, output_file, remove_prefixes):
 tensors = {}

 with safe_open(input_file, framework="pt", device="cpu") as f:
 metadata = f.metadata()
 for key in f.keys():
 if any(key.startswith(prefix) for prefix in remove_prefixes):
 print(f"Removing {key}")
 continue
 tensors[key] = f.get_tensor(key)
 save_file(tensors, output_file, metadata=metadata)

inputFile = "i:/ComfyUI_windows_portable/ComfyUI/models/loras/krea2/KNPV3_1.safetensors"
stripLayer = [
 # linked to the DIT/UNET
 'blocks', 'first', 'last_linear', 'last.linear'
 # liked to unet/DIT time MLP and timestep projection
 'tmlp_', 'tproj_1',
 # keep commented for NSFW
 #'txtfusion.layerwise_blocks', 'txtfusion_layerwise_blocks', # &lt;--- full censor
 #'txtfusion.projector', 'txtfusion_projector', # &lt;-- zero impact
 #'txtfusion.refiner', 'txtfusion_refiner', # &lt;-- tiny impact ==&gt; full censor
]
prefix = 'diffusion_model.'
stripLayer = [prefix+x for x in stripLayer]
print('layer to strip: ', stripLayer)

outPutFile = Path(inputFile).name

strip_layers(
 inputFile,
 outPutFile,
 stripLayer
)</code></pre>

NSFW Krea2 (Low VRAM)

Light VRAM Lora with only the text encode part. based on "<a target="_blank" rel="ugc" href="https://civitai.red/models/2728644/krea-2-mystic-xxx">Mystic XXX</a>" lora

Files with SHA256: d1d4961db16ee82dde072cb742f8cbc49222243b15c8656586d3649a6b8100df