Qwen3-VL-4B Heretic: Uncensored Text Encoder for Krea 2 in ComfyUI

news

DreamFast releases an uncensored Qwen3-VL-4B text encoder for ComfyUI, achieving 100% HarmBench ASR across BF16, FP8, INT8, NVFP4 and MXFP8 formats.

Qwen3-VL-4B-Instruct Heretic

DreamFast has released Qwen3-VL-4B-Instruct Heretic (ComfyUI), a fully abliterated version of the Qwen3-VL-4B-Instruct text encoder packaged specifically for ComfyUI. The model removes safety guardrails while preserving output quality, achieving a 100% HarmBench ASR (Attack Success Rate) compared to the base model's 30.8% — with minimal benchmark regression.

What is an Abliterated Text Encoder?

Abliteration is the process of selectively removing safety refusal circuits from a model without retraining. For image generation workflows like Krea 2, the text encoder interprets user prompts — and the stock Qwen3-VL-4B encoder rejects approximately 30% of prompted content. The Heretic variant eliminates these refusals while keeping the encoder's semantic understanding intact.

The forensic report shows a KL divergence of just 0.0283 (lower is better) and a GSM8K drop of only −1.83%, making it the least disruptive variant among all trials.

Five Quantization Formats

The model is available in five formats, covering everything from full precision to Blackwell-optimized 4-bit:

FormatSizeHardwareBest For
BF168.3 GBAny GPUMaximum fidelity
FP8 E4M34.2 GBAda+ (RTX 4090)Balanced speed and quality
INT8 ConvRot4.5 GBAny Ampere+ GPURecommended — near-lossless, no Blackwell required
NVFP4 E2M12.9 GBBlackwell (RTX 5090/5080)Smallest size, native FP4 tensor cores
MXFP84.7 GBBlackwellBest dynamic range with E8M0 block scales

The INT8 ConvRot variant uses SVD-guided learned rounding to minimize output error, making it the recommended pick for most users — it runs on any Ampere-or-later GPU without requiring Blackwell hardware.

Using with Krea 2 in ComfyUI

Krea 2 uses a Qwen3-VL-4B text encoder as its prompt interpreter. The Heretic checkpoint is a drop-in replacement:

  1. Download one of the .safetensors files from HuggingFace
  2. Place it in ComfyUI/models/text_encoders/
  3. Use the same loader node — the model uses the identical Qwen3-VL-4B architecture

The fp8 checkpoint (4.2 GB) is the closest match to the stock qwen3vl_4b_fp8_scaled.safetensors. For higher fidelity with uncensored prompts, use the int8 or bf16 variants.

Benchmark comparison across Heretic variants

Available Variants

The ComfyUI repo joins a family of three Heretic model distributions:

Community quantizers have already produced additional GGUF variants with over 1,000 combined downloads within hours of release.

Model Integrity

The abliteration only modifies 54 tensors (pure rank-1 edits), leaving the vast majority of the model untouched. MMLU score actually improved by +0.03% (69.61% vs 69.58%), while GSM8K dropped by just 1.83% — an acceptable trade-off for full uncensoring capability.

Note: This model removes safety alignment and will comply with harmful requests. Use it responsibly and in accordance with applicable laws and regulations.

Qwen3-VL-4B Heretic: Uncensored Text Encoder for Krea 2 in ComfyUI | ComfyUI Wiki