Evidaxis

Diffusers

repo incumbent
Media Generation · n = 14 · huggingface/diffusers
Calibration · conf low
momentum
momentum 90.3 of 100 90.3 /100
momentum
90.3/100
pctile
p100
convergence gate
Convergence gate: velocity only, citation axis absent ∅
gate
1 of 2 axes

velocity only, citation axis absent.

one axis passes
position in cohort distribution one of 14 in cohort
percentile 100 within cohort p25 p50 p75 p0 p100
percentile
p100
momentum is the combined velocity and citation signal, percentile within cohort
velocity z
velocity z gaugevelocity z+3.22 within cohort, log-slope +0.009/wk.0+3.22
velocity z
+3.22 σ
slope
+0.009/wk
log-slope +0.009/wk
convergence planefull gate = rising
Diffusers on the convergence plane Diffusers at velocity z +3.22 and citation z no axis, against 0 dual-axis cohort peers. single-axis: citation axis absent, excluded from the plane. z>=1 median velocity z → citation z ↑
velocity z
+3.22
citation z
no axis
peers
13

single-axis: citation axis absent, excluded from the plane.

citation z no citation axis
cohort
14
systems measured
weekly commits
22.8
rising trend
total citations
n/a
no axis
momentum
90.3
percentile p100
commit heatmap, last 26 weeks22.8/wk
weekly commits, 26 weeks26 weeks of commits, peak 30 in a week, 26 active weeks, 553 total.week 1: 26 commitsweek 2: 16 commitsweek 3: 15 commitsweek 4: 24 commitsweek 5: 17 commitsweek 6: 17 commitsweek 7: 25 commitsweek 8: 20 commitsweek 9: 21 commitsweek 10: 27 commitsweek 11: 12 commitsweek 12: 14 commitsweek 13: 19 commitsweek 14: 26 commitsweek 15: 18 commitsweek 16: 15 commitsweek 17: 30 commitsweek 18: 28 commitsweek 19: 25 commitsweek 20: 16 commitsweek 21: 17 commitsweek 22: 17 commitsweek 23: 30 commitsweek 24: 27 commitsweek 25: 29 commitsweek 26: 22 commits
weeks
26
peak/wk
30
active
26
total
553
citations by yearno axis
adoption 428 dependents 343 direct, 86 indirect · pypi/diffusers · deps.dev · adoption signal, not part of the momentum score

Diffusers holds an Evidaxis momentum score of 90.3 of 100 on methodology m2, snapshot 2026-08-08, measured within the Media Generation cohort (n = 14). It is a mature incumbent included to calibrate the cohort, measured but not gate-eligible.

Derived signals

second-order reads, computed from the published series

Three signals ship when the commit series is statistically sufficient; the rest are held in a reserved state until the data supports them. A reserved signal shows its reason, never a fabricated number. How these are computed.

recency-weighted swing trailing 13-week vs prior 39-week log-slope ratio +5.40, regime accelerating. prior slope +0.002, recent slope +0.012 per week. +0.002prior 39w+0.012recent 13w+5.40×
swing
+5.40×
regime
accelerating
windows
13w vs 39w
snapshot 1 of 1 · · m2
commit-axis Sharpe log-linear slope over residual std, value +0.016 with 95% CI -0.005 to +0.036, 50 degrees of freedom. CI spans zero.0+0.01695% CI -0.005, +0.036-0.005+0.036
sharpe
+0.016
95% ci
-0.005, +0.036
dof
50
snapshot 1 of 1 · · m2
commit changepoint52 weekly commit points. Changepoint at week 7 (2025-09-27), slope change +3.769 commits per week.2025-09-27
date
week
7 of 52
Δslope
+3.769/wk
snapshot 1 of 1 · · m2
code-leads-citation lag reserved

reserved: citation series too short / axis absent for cross-correlation

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
axis alpha vs cohort reserved

reserved: cohort N too small for regression (power ~0)

status
reserved
value
insufficient data
snapshot 1 of 1 · · m2
gate ETA reserved

reserved: needs snapshot history (1 snapshot exists)

status
reserved
value
insufficient history
snapshot 1 of 1 · · m2
methodology gate snapshot 1 of 1 · · m2
commit weeks
52
citation years
0
shipped
3
reserved
3

shipped

  • recency-swing
  • commit-sharpe
  • commit-changepoint

reserved

  • code-leads-citation-lag
  • axis-alpha
  • gate-eta
snapshot 1 of 1 · · m2

Adoption trend

Diffusers dependents over time6 points, range 412 to 428 dependents.
min
412 dependents
max
428 dependents
latest
428 dependents
points
6

Downstream packages depending on pypi/diffusers (deps.dev), captured point-in-time each snapshot. An adoption signal, not part of the momentum score.

Verdict

Diffusers is a mature incumbent included to calibrate its cohort. It is measured but not badge-eligible.

Sources

huggingface/diffusers development-velocity axis

Embed this badge

Evidaxis calibration, Diffusers
[![Evidaxis: Diffusers](https://evidaxis.org/badge/e_9VRK70WNP96/2026-w32.svg)](https://evidaxis.org/e/e_9VRK70WNP96)

Others in Media Generation

ACE-Step Media Generation
Single-axis
48
p38
vel -0.17 cit no axis
axis dials
-0.17 n/a
Fish Speech Media Generation
Single-axis
15
p15
vel -2.79 cit no axis
axis dials
-2.79 n/a
FLUX.1 Media Generation
Single-axis
52
p77
vel +0.17 cit no axis
axis dials
+0.17 n/a
HunyuanVideo Media Generation
Single-axis
88
p92
vel +3.02 cit no axis
axis dials
+3.02 n/a
Kokoro-82M Media Generation
Single-axis
49
p62
vel -0.06 cit no axis
axis dials
-0.06 n/a
LTX-Video Media Generation
Single-axis
50
p69
vel -0.00 cit no axis
axis dials
-0.00 n/a

Full Media Generation cohort →

entity_id e_9VRK70WNP96 methodology m2 snapshot 035a72a81e59 period 2026-w32 record JSON ↓ source snapshot

Score derived from public data on Evidaxis methodology m2, never edited by hand. Cite as: “Evidaxis, Diffusers, entity e_9VRK70WNP96, snapshot 2026-w32.”

Durable reference (format-independent): urn:evidaxis:claim:e_9VRK70WNP96:m2:2026-08-08