87 lines
4.3 KiB
Markdown
87 lines
4.3 KiB
Markdown
# FLUX 3 Image sampler/scheduler matrix
|
||
|
||
## Test conditions
|
||
|
||
- **Runs:** 432 (48 samplers × 9 schedulers)
|
||
- **Model:** `flux3-image-klein-int8-convrot.safetensors`
|
||
- **Text encoder:** `qwen3vl_4b_int8_convrot.safetensors` (`type=flux3`)
|
||
- **VAE:** `flux2-vae.safetensors`
|
||
- **Prompt:** [`prompt.txt`](prompt.txt), SHA-256 `5802909ebe894260b70a3977430e08aaa95732e0559749d8cb42e2f5ecf3ab6f`
|
||
- **Output:** 1088 × 1920 (the 1080 × 1920 target snapped to the model-compatible width)
|
||
- **Steps:** 4
|
||
- **Seed:** 310001
|
||
- **Result:** 432/432 successful
|
||
- **Total execution time:** 3726.104 seconds
|
||
- **Mean execution time:** 8.625 seconds
|
||
|
||
The complete per-cell record is in [`results/F3I-MATRIX.json`](results/F3I-MATRIX.json). Each cell contains the status, measured runtime, and the `F3I-M-SS-DD` output prefix used by the server, where `SS` is the sampler index and `DD` is the scheduler index.
|
||
|
||
## Runtime findings
|
||
|
||
Fastest sampler means across all nine schedulers:
|
||
|
||
- `TBG Flux2 Sampler` — 6.257 s
|
||
- `pid_sde` — 6.359 s
|
||
- `euler` — 6.407 s
|
||
- `dpm_fast` — 6.408 s
|
||
- `res_multistep` — 6.412 s
|
||
- `cfgpp_ud10_ab` — 6.415 s
|
||
- `ipndm` — 6.417 s
|
||
- `ipndm_v` — 6.424 s
|
||
- `ddim` — 6.428 s
|
||
- `dpmpp_2m` — 6.429 s
|
||
|
||
Scheduler means across all 48 samplers:
|
||
|
||
- `sgm_uniform` — 8.022 s
|
||
- `simple` — 8.063 s
|
||
- `linear_quadratic` — 8.265 s
|
||
- `beta` — 8.374 s
|
||
- `kl_optimal` — 8.816 s
|
||
- `karras` — 8.829 s
|
||
- `exponential` — 8.919 s
|
||
- `normal` — 8.921 s
|
||
- `ddim_uniform` — 9.417 s
|
||
|
||
`dpm_adaptive` is a clear runtime outlier. Its slowest cells were:
|
||
|
||
- `dpm_adaptive` + `ddim_uniform` — 87.590 s
|
||
- `dpm_adaptive` + `normal` — 61.760 s
|
||
- `dpm_adaptive` + `exponential` — 61.244 s
|
||
- `dpm_adaptive` + `kl_optimal` — 57.667 s
|
||
- `dpm_adaptive` + `karras` — 57.582 s
|
||
|
||
The fastest individual cell was `euler` + `exponential` at 6.199 s. Runtime alone is not a quality score.
|
||
|
||
## Visual spot-check
|
||
|
||
Representative generated images were inspected after the automated run:
|
||
|
||
- `F3I-M-01-01` (`euler` + `simple`) was a strong baseline: coherent subject, composition, anatomy, and useful prompt adherence.
|
||
- `F3I-M-01-04` (`euler` + `exponential`) was visibly degraded in the inspected sample, with garbled scoreboard text and smeared detail.
|
||
- `F3I-M-16-05` (`dpm_adaptive` + `ddim_uniform`) showed severe anatomy duplication/extra limbs, garbled text, and texture artifacts.
|
||
- `F3I-M-48-09` (`uni_pc_bh2` + `kl_optimal`) was overprocessed in the inspected sample, with distorted texture/anatomy and garbled text.
|
||
|
||
These are representative spot-checks, not a claim that four images fully rank all 432 outputs. The matrix proves that every combination executes successfully on the installed local model; a full perceptual ranking would require reviewing all 432 images or adding an image-quality scoring pass.
|
||
|
||
## Recommendation
|
||
|
||
Keep **Euler + Simple** as the default comparison baseline. It is fast, already aligned with the native workflow path, and produced the strongest inspected sample. Treat `sgm_uniform` as a similarly fast scheduler candidate for follow-up visual testing. Avoid `dpm_adaptive` for routine generation because its runtime is unpredictable and its inspected sample was poor. Keep the remaining combinations available as experimental options until they receive visual review.
|
||
|
||
No generated server files were deleted during collection. The matrix outputs remain under the server prefix `fluxExperiments/flux3image/matrix/` so the visual findings can be revisited.
|
||
|
||
## Best five reviewed outputs
|
||
|
||
These are the five strongest images from the visual review, ordered best first.
|
||
They are copied into [`results/best5/`](results/best5/).
|
||
|
||
1. [`01-euler-simple.png`](results/best5/01-euler-simple.png) — `euler` + `simple`
|
||
2. [`02-euler-sgm_uniform.png`](results/best5/02-euler-sgm_uniform.png) — `euler` + `sgm_uniform`
|
||
3. [`03-dpmpp_2m-simple.png`](results/best5/03-dpmpp_2m-simple.png) — `dpmpp_2m` + `simple`
|
||
4. [`04-res_multistep-simple.png`](results/best5/04-res_multistep-simple.png) — `res_multistep` + `simple`
|
||
5. [`05-ddim-simple.png`](results/best5/05-ddim-simple.png) — `ddim` + `simple`
|
||
|
||
The first two are very close in appearance because this low-step configuration
|
||
produced nearly identical results for those cells. The ranking is a visual
|
||
selection, not a statistically significant model-quality benchmark.
|