LoganBooker / SesquiLSR
Arbitrary scale latent upscaler for SDXL, Flux, Flux2, and Wan 2.1/Anima/Qwen Image. Supports fractional scaling up to 2.0x. Includes ComfyUI node and pretrained weights.
Why this job: says: comfyui; topics: stable-diffusion, comfyui
What it does
- Multi-model support. SDXL, Flux, Z-Image Turbo, Flux2 Klein, Krea 2, Wan 2.1, Qwen Image and Anima from a single architecture
- Arbitrary scale in [1.0x, 2.0x]. not limited to fixed 2x
- ~3M parameters, ~12MB weights across all variants
- Sub-6ms inference in latent space, with no VAE round-trip
- ComfyUI node included. drop-in, no model or VAE connection required
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 35 days ago
- Stars
- 117
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 57% closed
- 3 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Stability-AI / stability-sdk | 2,438 | 5 months ago | MIT | No downloads |
| Comfy-Org / comfy-cli | 1,048 | yesterday | GPL-3.0 | No downloads |
| YanWenKun / ComfyUI-Windows-Portable | 623 | 23 days ago | GPL-3.0 | Windows |
More: languages, topics and project record
Languages
- Python 100%
Topics
- comfyui
- latent-diffusion
- latent-space
- stable-diffusion
- super-resolution
- upscaler
- upscaling
Project record
- JobImage generation
- StatusListed
- Commits16
- Forks7
- Watching1
- Stars in 28 days+10
- CreatedJun 10, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026