WeReCooking/flux2-klein-4B-uncensored-text-encoder

This is a duplicate of Cordux/flux2-klein-4B-uncensored-text-encoder for Flux-Klein-4B-CPU Space

Qwen3-4B Ablated (Uncensored) Text Encoder - GGUF Q4_0

Uncensored/ablated version of Qwen3-4B text encoder in GGUF Q4_0 format for Flux2 Klein 4B models.

Compatible Models

• —Flux2 Klein 4B (Distilled & Base)

What This Does

This is an ablated (safety-filtering removed) text encoder that allows Flux2 Klein models to generate NSFW content without prompt censorship.<br> The base Qwen3-4B text encoder that ships with Flux2 Klein has safety filtering that prevents certain prompts from being processed properly.

Installation

1. 1.Download qwen3-4b-abl-q4_0.gguf
2. 2.Place in ComfyUI/models/text_encoders/ or ComfyUI/models/unet/ (for GGUF loaders)
3. 3.In your workflow, use a GGUF-compatible text encoder loader node
4. 4.Point it to this file instead of the default Qwen3-4B

Prompting Tips

• —Use "wearing nothing" instead of "naked/nude" for best nude results
• —The model looks for clothing descriptors - even "nothing" counts as one
• —Clinical terms like "vagina" don't work better than colloquial terms
• —For explicit content beyond nudity, you'll need an NSFW LoRA

Language-Style Mapping Research

I discovered Flux.2 Klein associates languages with specific styles: <br> Japanese→anime portraits, German→illustrated art, etc.<br> Full study here

Limitations

This removes prompt filtering but doesn't add visual knowledge. The base Flux2 Klein models have limited training on explicit content, so:

• —✅ Nudity works well
• —✅ Suggestive poses work
• —❌ Explicit anatomy requires a LoRA
• —❌ Sexual acts require a LoRA

Credits

• —Based on huihui-ai/Qwen3-4B-abliterated
• —Converted with llama.cpp