Every loader uses type qwenimage and feeds TextEncodeQwenImage21. Qwen-Image-2.1 is a full (non-distilled) model — use ~20–30 steps. 1. Install the add-on (you also need city96/ComfyUI-GGUF): 2. Put both files in ComfyUI/models/textencoders/ - qwen3vl8bheretic-Q4KM.gguf - mmproj-qwen3vl8bheretic-f16.gguf ← the vision tower (required — also used for image editing) Don't rename either file — the vision tower is matched by name. If it's missing, the add-on stops with a Missing vision tower error telling you which file to download. 3. Restart ComfyUI, then CLIPLoaderGGUF → type qwenimage → TextEncodeQwenImage21 → the rest of the official workflow. The console should show [GGUF-Qwen3VL-TE] added…
Independent publisher
Pottokao
pottokao
photography
Models in Library5
Datasets in Library0
Models on Hugging Face28
Followers33
Models
The text encoder of Qwen/Qwen-Image-2.1 (a Qwen3-VL-8B-Instruct) with refusal behaviour removed via Heretic directional ablation. Drop-in replacement for the stock text encoder. Weights are bf16, same shapes, same parameter count — nothing else was changed. Measured by Heretic on mlabonne/harmfulbehaviors (test split) for refusals and mlabonne/harmlessalpaca for KL divergence — i.e. lower refusals and lower distribution shift on benign inputs. Refusal rate and general capability were re-checked with a separate script (different code, different refusal keyword set) rather than trusting the (e.g. "What is the capital of France?" → "The capital of France is Paris…") Heretic's documented…
NVFP4 (4-bit weight) build of Qwen-Image-2.1-Text-Encoder-Heretic, the abliterated text encoder of Qwen/Qwen-Image-2.1. File: qwen3vl8bnvfp4heretic.safetensors — 5.87 GB (from 16.33 GB bf16) Produced with Heretic directional ablation (oproj + downproj), 200 trials / 60 startup trials, knee point of the Pareto front. Measured on mlabonne/harmfulbehaviors (refusals) and mlabonne/harmlessalpaca (KL). Independently re-checked on the bf16 source: 0/20 refusals, 4/4 benign questions answered correctly. Full methodology, Pareto table and reproduction command are in the Blackwell GPUs (RTX 50xx, GB10). NVFP4 maps onto native FP4 tensor cores, so you get both the memory saving and a throughput win.…
INT8-convrot build of Qwen-Image-2.1-Text-Encoder-Heretic, the abliterated text encoder of Qwen/Qwen-Image-2.1. File: qwen3vl8bint8convrotheretic.safetensors — 8.71 GB (from 16.33 GB bf16) This is the format Comfy-Org's official Qwen-Image-2.1 templates use by default (qwen3vl8bint8convrot.safetensors). If you followed any official / community Qwen-Image-2.1 tutorial, this is a drop-in replacement — just swap the filename. It keeps every projection at INT8 (heavier than the 4-bit W4A8 build, but the most faithful to the stock template). Produced with Heretic directional ablation (oproj + downproj), 200 trials / 60 startup trials, knee point of the Pareto front. Measured on…
Asymmetric W4A8 INT8 build of Qwen-Image-2.1-Text-Encoder-Heretic, the abliterated text encoder of Qwen/Qwen-Image-2.1. File: qwen3vl8bw4a8heretic.safetensors — 5.88 GB (from 16.33 GB bf16) Comfy-Org ships this format too, so it loads with the stock CLIPLoader. This is the smallest safetensors build here (6 GB). If you just want the exact format the official ComfyUI templates load by default — the "swap the filename and it works" option — use the instead; this W4A8 is the pick when you want a smaller file. Produced with Heretic directional ablation (oproj + downproj), 200 trials / 60 startup trials, knee point of the Pareto front. Measured on mlabonne/harmfulbehaviors (refusals) and…