| --- |
| license: other |
| license_name: qwen-research |
| license_link: LICENSE |
| base_model: |
| - Qwen/Qwen-Image-2.1-PE-T2I |
| pipeline_tag: text-to-image |
| tags: |
| - heretic |
| - abliterated |
| - prompt-rewriting |
| - text-to-image |
| - qwen-image |
| --- |
| |
| # Qwen-Image-2.1-PE-T2I Heretic (abliterated) |
|
|
| > **Not affiliated with or endorsed by Alibaba / Qwen.** A community derivative of |
| > [`Qwen/Qwen-Image-2.1-PE-T2I`](https://huggingface.co/Qwen/Qwen-Image-2.1-PE-T2I), redistributed under the |
| > **Qwen Research License** (copy included as `LICENSE`). **Non-commercial use only**; commercial use needs a separate |
| > licence from Qwen. |
|
|
| The **text-to-image prompt rewriter** for Qwen-Image-2.1, a fine-tuned Qwen3.5-VL 9B that turns a short request into |
| a detailed English prompt plus a recommended aspect ratio, with its refusal behaviour reduced by |
| [Heretic](https://github.com/p-e-w/heretic) directional ablation. bf16, same shapes and parameter count as the source. |
|
|
| **`system_prompt.txt` is included and required** (the unmodified file from the source repo). |
| |
| Companion: [darrellbest/Qwen-Image-2.1-PE-I2I-Heretic](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-I2I-Heretic) |
| for image edits. |
| |
| ## Results |
| |
| | | Refusals | KL divergence | |
| |---|---:|---:| |
| | Original | 98/100 | 0 *(by definition)* | |
| | **This model**, re-measured after export | **31/100** | **0.0130** | |
| | This model's trial during the search | 24/100 | 0.0131 | |
| |
| Measured by Heretic on `mlabonne/harmful_behaviors` (refusals) and `mlabonne/harmless_alpaca` (KL divergence, the |
| damage to ordinary behaviour), with Heretic's default system prompt. The first row is an independent evaluation of the |
| exported weights (`evaluate_model`); the search's own figure for the same trial was 24/100. The KL matches exactly; |
| the refusal gap is within about 1.6σ at n = 100. For reference, the same evaluation of |
| [pottokao/Qwen-Image-2.1-PE-T2I-Heretic](https://huggingface.co/pottokao/Qwen-Image-2.1-PE-T2I-Heretic) measured |
| 5/100 at KL 0.0349 (its card: 3/100, 0.036), a stronger ablation with more side effects. |
| |
| **This is a light-touch ablation.** Across 1,000 trials the search's Pareto front bottomed out at 23/100 refusals, so |
| this model keeps roughly a quarter to a third of the original's chat-style refusals, while changing its ordinary behaviour less than |
| most ablations (KL 0.013; for comparison the I2I companion is 9/100 at KL 0.037). If you need fewer refusals, pick a |
| stronger ablation. Pareto front of the search: |
|
|
| | Refusals | KL | | |
| |---:|---:|---| |
| | 23/100 | 0.0194 | trial 228 | |
| | **24/100** | **0.0131** | **trial 225 (this model)** | |
| | 30/100 | 0.0089 | trial 223 | |
| | 36/100 | 0.0085 | trial 245 | |
| | 46/100 | 0.0044 | trial 231 | |
|
|
| With n = 100 the refusal count is noisy (σ ≈ 4 here), so 23 vs 24 is no difference; 225 was chosen for its lower KL. |
|
|
| ## Does it still rewrite prompts? |
|
|
| Checked through a real image app's prompt-enhancer path (the official `pe_core` output contract, `enable_thinking`, |
| Qwen's sampling settings) on a plain request and two borderline ones (a horror poster with a bloodied survivor; a |
| soldier aiming a rifle). Every answer parsed, with a detailed prompt and an aspect ratio. As with the other |
| Qwen-Image-2.1 rewriters, the original is already relaxed about edgy image subjects; the ablation mainly changes its |
| refusals of chat-style harmful instructions, which is what the 98/100 baseline measures. |
|
|
| NVFP4 build for vLLM on Blackwell: |
| [darrellbest/Qwen-Image-2.1-PE-T2I-Heretic-NVFP4](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-T2I-Heretic-NVFP4). |
|
|
| ## Reproduce |
|
|
| - Heretic `3521f86` (main, 2026-09-21), default config except `n_trials = 1000` and `export_strategy = "merge"`. |
| transformers 5.17.0, torch 2.11.0+cu130, one RTX PRO 6000 Blackwell. |
| - Trial 225 parameters: `direction_scope = global`, `direction_index = 17.498`, |
| `attn.o_proj: max_weight 1.49 at 21.632, min_weight 0.958, min_weight_distance 16.843`, |
| `mlp.down_proj: max_weight 1.452 at 21.259, min_weight 0.001, min_weight_distance 10.638`. |
|
|
| ## Use |
|
|
| Exactly like the original: load with `AutoModelForImageTextToText` / `AutoProcessor` and use `system_prompt.txt` as |
| the system prompt. |
|
|
|
|
| ## The family |
|
|
| | Model | Format | Use it with | |
| |---|---|---| |
| | [PE-T2I-Heretic](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-T2I-Heretic) | bf16 safetensors | transformers / diffusers | |
| | [PE-T2I-Heretic-GGUF](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-T2I-Heretic-GGUF) | GGUF BF16 / Q8_0 / Q4_K_M | llama.cpp, Ollama | |
| | [PE-T2I-Heretic-NVFP4](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-T2I-Heretic-NVFP4) | NVFP4 (compressed-tensors) | vLLM on Blackwell | |
| | [PE-I2I-Heretic](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-I2I-Heretic) | bf16 safetensors | transformers / diffusers | |
| | [PE-I2I-Heretic-GGUF](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-I2I-Heretic-GGUF) | GGUF BF16 / Q8_0 / Q4_K_M (+ mmproj) | llama.cpp, Ollama | |
| | [PE-I2I-Heretic-NVFP4](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-I2I-Heretic-NVFP4) | NVFP4 (compressed-tensors) | vLLM on Blackwell || [PE-Heretic-ComfyUI](https://huggingface.co/darrellbest/Qwen-Image-2.1-PE-Heretic-ComfyUI) | single-file safetensors (T2I + I2I) | ComfyUI | |
|
|
| **T2I** rewrites a short request into a detailed prompt for new images; **I2I** rewrites an edit instruction, reading the |
| image being edited. Both are prompt rewriters for [Qwen-Image-2.1](https://huggingface.co/Qwen/Qwen-Image-2.1), not |
| image generators. |
|
|
