2025-11-08 03-09-06 (0-00-14-28)Still work in progress, checkpoints are being uploaded on the go
Current best: LoRA A: qwen-edit-enhance_64-v3_000001000, LoRA B: qwen-edit-enhance_000004250
LoRA A and LoRA B are meant to be wired one after another
Comfy workflow
is in the filesPrompt:
Enhance image quality, followed by textual description of the scene. The more descriptive it is, the better the upscale effect will be
All images below are from 8 step Lighting LoRA.
- ModelSamplingAuraFlow is a must, shift must be kept below 0.3. With higher resolutions, such as image 3, you can set it as low as 0.02
- Samplers - LCM (best), Euler_Ancestral, then Euler
- Schedulers all work and give varying results in terms of smoothness
Trained on a filtered subset of Unsplash-Lite and UltraHR-100K at 2.4MP
- Style: photography
- Subjects include: landscapes, architecture, interiors, portraits, plants, vehicles, abstract photos, man-made objects, food
- Trained to recover from:
- Low resolution up to 16x
- Oversharpened images
- Noise up to 50%
- Gaussian blur radius up to 3px
- JPEG artifacts with quality as low as 5%
- Motion blur up to 64px
- Pixelation up to 16x
- Color bands up to 3 bits
- Images after upscale models - up to 16x
Not trained on: 2d, illustrations, artworks, text, graphics, CGI
2025-11-08 03-09-07 (0-00-02-28)
2025-11-08 03-09-06 (0-00-29-02)
2025-11-08 03-09-06 (0-00-35-15)
2025-11-08 03-09-06 (0-00-56-16)
2025-11-08 03-09-06 (0-01-09-04)
