If you like my content, support me at:
https://ko-fi.com/duchaiten
Patreon is here (but there's nothing in it):
https://linktr.ee/Duc_Haiten
I created my Discord server. I'm still quite new to Discord server management, feel free to share your opinions.
https://discord.gg/vKEW6jqa49
v0.3 makes more realistic and more cosplay data
Beta_v0.2 is a version that adds a lot of anime data. It slightly suppresses the NSFW data, and the real 3D material is also affected a bit, but since it's just a beta version, it's fine. I’ll try different directions to see which one people like the most.
This model was retrained from Qwen image for a full month (counting only continuous training time). I haven’t finished it yet, but since it’s been taking way too long, I decided to release the beta version first. It seems that Qwen doesn’t work with A1111 or ForgeUI yet, so I ran it on ComfyUI instead. Anyway, I hope everyone enjoys this new model after such a long break — if you run into any issues, please let me know.
Oh, and about the sample images — there are some things I didn’t do in them, but that doesn’t mean the model can’t do those things or that it needs a LoRA. You know what I mean 😉.
(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, cropped, extra limb, missing limbs, deformed hands, long neck, long body, signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist
About Us — LahGenAI
Our team includes known creators in the AI art and workflow community such as: @Lah_Inthe_Futureland , @DucHaiten, @Hius, ChugAx from shakker and @Hideroki
Visit us at: https://lahteam.vn
Our Services
We specialize in:
Finetuning Checkpoints and LoRAs for image and video applications.
Building ComfyUI workflows for image/video processing and integrating them into AI production pipelines.
Deploying and packaging AI products, including solution consulting and product development support for startups.
If you need to build a stable, scalable visual AI pipeline, we can support your team end-to-end.
Description
FAQ
Comments (11)
Will try this right away!,annoys me how simple stuff like one nipple out qwen can't do,btw,you don't have plans for Chroma?
duchaiten sex y qwen beta 0.2 include beta 0.1? and can me using that for i2i?
if you want more heavy nsfw then use the first beta, which is v0.1. version two has 2.5d data and more anime just to add favorite characters and anime-like aura and light color feeling, it overrides nsfw quite a lot
can it do realism?
I'm working on version 0.3 which is more realistic
@DucHaiten yay thank you
Just the thing I was looking for as qwen doesnt do 3d very well and is censored so many lora doesnt work with 2d loras artstyle and this model has soo dang good uncensored generation, but considering the size of qwen being 20gigs having a 20gigs model for diff style takes a lot of space, any plains for lora?
I'm planning to make a new base model for qwen and then make dedicated loras for it. It needs to do well first before starting to create a lora ecosystem around it.
@DucHaiten I think he meant lora extracted from this checkpoint
Regarding your description... There is a fork of A1111/Webforge called Neo that supports Qwen & WAN: https://github.com/Haoming02/sd-webui-forge-classic/tree/neo
niceee thank you