CompVis/latent-diffusionGitHub
calls DemoFusion “progressive multi-scale fusion to extend existing diffusion models to megapixel outputs without retraining”
High-Resolution Image Synthesis with Latent Diffusion Models
14.2kJupyter Notebookdormant
PRIS-CV/DemoFusion Alternatives
DemoFusion is queued for analysis. Crawling candidates and ranking them takes a few minutes. This page updates itself when the list exists — you can also come back later.
What is known so far comes from the other direction:
Listed as an alternative to
These projects were analysed and named DemoFusion among their alternatives. The relationship is not symmetric — how DemoFusion rates them is a separate judgement, made when DemoFusion is analysed in its own right.
CompVis/taming-transformersGitHub
calls DemoFusion “Choose for patch-based diffusion high-resolution generation if you do not want a VQGAN+transformer pipeline.”
Taming Transformers for High-Resolution Image Synthesis
6.5kJupyter Notebookdormant
NVlabs/SanaGitHub
calls DemoFusion “Choose when you already have Stable Diffusion/SDXL weights and only need training-free high-resolution extension, not a full Sana-class generator.”
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
9.1kPythonactive