V1.6 FP8 released
This is an experimental quantization weight implemented by scaling the maximum value in V1.6 to run on low GPU memory.
Recommended for use with Qwen-Image-Edit-2511-Lightning-4steps-v1.0-fp32.
Suggested sampler: Euler + Simple
🤯🤯 2026-01.01 Happy New Year - V1.6
V1.6 reduces the NSFW LoRA components and adds F2P LoRA.
Based on testing:
Improved facial consistency.
More harmonious female body proportions.
Tested and performs well for body solo display, oral sex, doggy style, cowgirl, missionary, masturbation, titjob, and footjob (except anal).
Anime generation may still show a mismatch where characters appear 2D while scenes appear 3D; please be aware when generating anime images.
Workflow download
v1.6
v1.2
v1.5
## 🔄 Update Log / Changelog
2025.12.31
I take back what I said yesterday. The bf16-no-lightning version of v1.5 performed unsatisfactorily. It seems that the model encountered problems even with just 20 steps of raw image processing, and the quantized and accelerated model naturally inherited these issues.
I've decided to focus my work on optimizing v1.6.
abliterated will mainly include three types of weights:
An original FP16/BF16 version
An original FP8 quantized version
An FP8 & 4steps version
2025.12.30
Based on community feedback and suggestions, future releases of qwen-image-abliterated will mainly include two types of weights:
An FP16/BF16 version
An FP8 quantized version
Considering that Lightning (acceleration) lora may negatively affect users who require more fine-grained image generation, future versions will no longer integrate acceleration LoRAs into the base model by default.
If faster inference is needed, users may add acceleration lora nodes manually.
That’s all.
At present, v1.5-bf16-no-lightning is being uploaded, and v1.5-fp8-no-lightning will follow.
The v1.6 version is currently in preparation.
Current known issues:
Facial consistency shows a bias toward Caucasian features
Anime image generation exhibits an overly 3D-like appearance
Exaggerated expressions in side-view generations, possibly related to LoRAs
Unesthetic limb proportions, such as short legs or short arms
The generated image has a single lens.
The error rate for limb abnormalities is much higher than in version 1.2.
These issues will be a key focus in the v1.6 iteration. We will collect and merge more LoRAs, and we also look forward to qwen-image-edit releasing an improved version.
repository Name Changed
This repository has been officially renamed Qwn-Image-Edit-abliterated. Due to Civitai's model naming conventions, the previous qwnImageEdit2509_v15Fp8mixed4step.safetensors was actually version qwen-edit-2511. Similarly, the download model names for versions v1.4bf16-4step and v1.5fp8mixed-4step have changed as follows:
qwnImageEdit2509_v15Fp8mixed4step.safetensors -> qwnImageEdit_v15Fp8mixed4step.safetensors
qwnImageEdit2509_v14Bf164steps.safetensors -> qwnImageEdit_v14Bf164steps.safetensors
It is recommended to rename them to qwen-image-edit-abliterated-v1.5-fp8-4step and... The qwen-image-edit-abliterated-v1.4-bf16-4step .
The example workflow will be available in two versions: V1.5 qwen-image-edit-2511 and V1.2 qwen-image-edit-2509.
I noticed that ComfyUI released a workflow specifically for qwen-2511, which might replace the original workflow.
🎉 V1.5 - 2025.12.29
This may be the best-performing version since its creation.
What is it?
It is built on qwen-image-edit-2511.
It offers excellent character consistency control.
It provides native FP8 quantization support, with extremely low image quality loss compared to merging weights directly into a quantized model.
It enables stable NSFW image generation and works well with both long prompts and short keyword triggers.
At the same time, its strong consistency effectively resolves the issue of yellowish or dull female skin tones, keeping them closely aligned with the original image’s skin color.
It performs effortlessly on both anime and realistic styles.
In addition, v1.5 has merged 4-step acceleration weights, allowing the use of Euler + sampler with 4 steps.
v1.4 - 2025-12.28
Status: Released
Based on my testing, v1.4 is an unstable release and shows higher randomness compared to v1.3. v1.5 is expected to be a stable release.
Improvements
đź’Ş Created using qwen-image-edit-2511
🧑‍💼 Better male nude performance
Use Note
Keeping the female protagonist’s face, appearance, and bust size consistent in the image is not necessary, especially when generating images from a rear-view perspective.
The biggest difference between v1.4 and v1.3 is that v1.4 retains the instruction-following capability of qwen-2511. Both overly detailed prompts and overly sparse prompts can lead to results that do not meet expectations.
In addition, I lowered the weight of NSFW LoRAs, because qwen-2511 is extremely sensitive to these LoRAs. As a result, sexual terms that were effective in v1.3 are not as influential in v1.4.
Based on testing, v1.4 requires more detailed descriptions of female poses and male poses. When the descriptions are done well, the resulting image quality is also very high.
In summary, v1.4 requires more advanced and nuanced prompt techniques than v1.3, but it produces more precise and accurate images.
### v1.2 — 2025-12-16
Status: Released
Improvements
🎨 Improved *anime-style consistency**
🧍 More *complete and anatomically correct male bodies**
Qwen-Edit-2509-Abliterated Model Card
Despite the existence of many unreviewed LoRAs and checkpoints based on qwen-image-edit, the image quality during actual usage is still not ideal. Especially for NSFW merge-model creation, adding too many LoRAs with arbitrary weights often damages the original semantic capability of qwen-image-edit.
Let’s introduce Qwen-Edit-2509-Abliterated.
What is it?
Qwen-Edit-2509-Abliterated is a merged model created by combining the Qwen-Edit-2509 unet checkpoint with various community LoRAs. It integrates multiple NSFW LoRAs, along with functional LoRAs such as camera-angle transformation, color tone reference, and image quality enhancement. The goal is to improve Qwen-Edit’s understanding of human poses and shooting perspectives during image editing.
As its name suggests, this is a model without review mechanisms. It can generate NSFW and unreviewed content.
The model creator is not responsible for any outputs produced. Users are encouraged to use this checkpoint friendly, legally, and responsibly.
The merged model has quantized in FP8.
The model has Supports 4-step accelerated sampling.
1. About accelerator selection
When comparing merge models with similar purposes, we found that most NSFW LoRAs were originally trained on qwen-image, a model designed for image generation.
However, accelerators used for these merge models are often from qwen-image-edit.
Tests showed:
- qwen-image-edit accelerators often fail during NSFW generation
- This may result in incomplete characters or “broken images”
- Recent testing suggests that the qwen-image accelerator performs much better for LoRA acceleration than the native qwen-image-edit one
Therefore, v1.0 uses the qwen-image accelerator, though this still requires further validation.
## Some of my personal insights on LoRA merging
2. About LoRA weight selection
The LoRA weights used in merging are all kept small (usually 0.1–0.4).
This seems to preserve most of qwen-image-edit’s original semantic understanding.
In actual usage, the experience has been very good.
Have fun!
Description
FAQ
Comments (17)
Great work, thanks, any chance to release an fp16 version?
The FP16 is still in the planning stages,stay tuned.
@ddpm_jcc yes fp16 would be preferred if you can
After a bit of Testing: best nsfw model i experienced so far. Far better nsfw Generations than nsfw aio Models and Base + any loras i threw at it.
I have only one complaint so far: Like refined sdXL Models this qwen model Trends to feminize many of The males prompted, Generating more feminine faces and often female nipples, which Is hard to counter unless you force beards and chest hair. This dies Not occur with AIO nsfw Models.
Still, The prompt adherence ist unmatched, which makes me Switch Back to qwen (from zimage).
So far i think Euler beta57 @ 3-steps + additional 2 steps staring at step 9 ist the best setting (still Testing)
The issue of male characters developing female breasts does indeed exist. In practice, when I use it, I usually only depict male characters from the lower body down to create NSFW scenes. Perhaps in the future there will be a more well-balanced male body LoRA to improve this problem.
@ddpm_jcc Just in case you are still collecting good loras - this one did a very good job without compromising female genitalia: https://civitai.com/models/2126408?modelVersionId=2451507
@Adaptalab0r Yes, I will try this.
Cool thanks, but a bit ironic to see your abliterated model and the new qwen 2511 on the same day, but thank you. Will you make the same for the new qwen edit? I prefer to have full weights but I know that some LoRA only available in fp8
Yes, I see the new model released, I will try merge a model in 2511
@ddpm_jcc oooh yes. following for this
@ddpm_jcc Awesome!!! Can you maybe throw this in the mix? Maybe it yould help fix "female faces/nipples on males" issue : https://civitai.com/models/2126408?modelVersionId=2451507
@Adaptalab0r Yes, I will try this.
@ddpm_jcc amazing
Will there be a quant version too?
yes,I will upload version 16 first.
Great! but sad that 2511 was soon released.. will you make a 2511 version too?
Yes, model v1.4 is being uploaded. It's based on the unapproved model 2511, first bf16, then fp8.