Analysis of Classifier-Free Guidance Weight Schedulers

### Model/Pipeline/Scheduler description

The paper's authors performs an analysis and proposes 1 line change in order to make Classifier-Free Guidance looks better

I personally run some test to confirm

**SD1.5 DDIM scheduler, 50 steps, "a photograph of an astronaut riding a horse", seed: 1024**
guidance scale: 7.5
static

linear (proposed)

guidance scale: 14.0
static

linear (proposed)

### Open source status

- [ ] The model implementation is available.
- [ ] The model weights are available (Only relevant if addition is not a scheduler).

### Provide useful links for the implementation

Paper: https://arxiv.org/abs/2404.13040

Start with the linked paper and inspect the DDIM scheduler entry point; the issue names no file or test. Reproduce the stated SD1.5 experiments, then establish the exact scheduler change and validation needed for the proposed guidance-weight behavior.

Vom Indexierungsmodell aus dem Issue-Text verfasst.