v3: Cleaner, more eye-catching, more vibrant... otherwise it has the same features as v2. all settings are the same...
v2: Created using Qwen Image 2512. Produces extremely realistic and detailed images. Provides cleaner outputs compared to the first version. Ideal for NSFW content but not very creative for hardcore scenes.
v1: This is my first qwen share. It was created to achieve realistic and cinematic style visuals. It may not be suitable for anime-style visuals. It is EXTREMELY suitable for NSFW style content. Despite its large size, it is extremely fast. I created it for fast use. If you are going to use it with LORAs, keep the LORA weight values very low. Otherwise, the images you create may be distorted.
The most suitable usage I have found:
Steps: 6-8
cfg: 1
Resolution: 1328x1328 or 1440x1440 resolution and 2:3, 3:4, 16:9, 1:1, and all other ratios
Sampler: Euler a + beta/ bong tangent/ DDIM Uniform
Sigma Shift: 2-3
Using these settings, it takes about 25-30 seconds to generate an image at 1440x1440 resolution and 8 steps on my RTX3090 computer.
IMPORTANT: If you use settings other than the ones I provided (different samplers other than Euler-A, clip skip:2, high-value LORAs, high sigma shift values, etc.), you will most likely get corrupted images.
Description
This is identical to v2.0, but is the most refined version with the VAE and CLIP models removed, resulting in a size of 19GB.
FAQ
Comments (12)
from the generation settings I assume it has lightning loras included? Is ther also a version with those? :)
I added 4step lightning lora and some other loras to the Qwen image version 2512. I created it in a realistic photo style and suitable for NSFW. Another version will probably be coming this weekend. gguf versions will not be coming.
would you post a version without the lightning loras?
@bewunderteradler112 The version without Loras is the default 38GB version. You can download it here: https://civitai.com/models/2268063?modelVersionId=2552957
@53rt5355iz Thanks :) but isnt that the original version? I bet you mixed more into your masterpiece than "just" the lightning loras ;)
@bewunderteradler112 Sure. I used 6 Loras. One of them is a Lightning Lora. The weight values of the other Loras range from 0.3 to 0.7. But I created a single model by using them all together. I published that too. So I didn't create a model first and then include the Lightning Lora in it.
Smaller lighter GGUF Q2 version????
Unfortunately, I can only convert to FP8.
Silly question but do i save this in the checkpoint or diffusion model folder in ComfyUI?
Yes
How about an FP16 model? ;)
With the approximately 40GB fp16 model, I didn't see much difference in performance and quality compared to the fp8 model, so I found it unnecessary and deleted it. Since uploading it here would take me too long, I didn't even consider it.