4.3 KiB
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, SHA-2565802909ebe894260b70a3977430e08aaa95732e0559749d8cb42e2f5ecf3ab6f - 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. 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 spid_sde— 6.359 seuler— 6.407 sdpm_fast— 6.408 sres_multistep— 6.412 scfgpp_ud10_ab— 6.415 sipndm— 6.417 sipndm_v— 6.424 sddim— 6.428 sdpmpp_2m— 6.429 s
Scheduler means across all 48 samplers:
sgm_uniform— 8.022 ssimple— 8.063 slinear_quadratic— 8.265 sbeta— 8.374 skl_optimal— 8.816 skarras— 8.829 sexponential— 8.919 snormal— 8.921 sddim_uniform— 9.417 s
dpm_adaptive is a clear runtime outlier. Its slowest cells were:
dpm_adaptive+ddim_uniform— 87.590 sdpm_adaptive+normal— 61.760 sdpm_adaptive+exponential— 61.244 sdpm_adaptive+kl_optimal— 57.667 sdpm_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/.
01-euler-simple.png—euler+simple02-euler-sgm_uniform.png—euler+sgm_uniform03-dpmpp_2m-simple.png—dpmpp_2m+simple04-res_multistep-simple.png—res_multistep+simple05-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.