3.2 KiB
Flux.2 Klein 9B — optimized T2I
This is the current best tested Flux.2 Klein text-to-image workflow for the 8 GB RTX 3070.
Files:
workflow.json— API-format prompt for/promptautomation.ui-workflow.json— native ComfyUI workflow; load it from the web UI with Load.
Settings
- Model:
flux-2-klein-9b-fp8mixed.safetensors - Text encoder:
qwen_3_8b_fp8mixed.safetensors(flux2) - VAE:
flux2-vae.safetensors - Resolution: 1080×1920, 9:16 portrait
- Sampler:
euler_cfg_pp - Steps: 6
- CFG: 1.3
- Seed:
20260920 - Measured generation time: approximately 220.3 seconds for the current best (F-T2I-03).
The included seed and prompt are a controlled baseline example. For reuse, replace the prompt, seed, and resolution; sampler, scheduler, steps, and CFG are the optimization controls.
The positive prompt is the shared T2I comparison prompt in ../prompt.txt, also used by the Qwen workflow.
Planned optimization matrix
All rows are intentionally Untested. Keep the prompt, seed, and resolution from ../variables.json fixed. Flux2Scheduler does not expose a selectable scheduler, so that value remains fixed.
| ID | CFG | Steps | Sampler | Scheduler | Runtime (s) | Tested? | Current Best |
|---|---|---|---|---|---|---|---|
| F-T2I-01 | 1.3 | 6 | euler_cfg_pp | Flux2Scheduler | 263.9 | Yes | No |
| F-T2I-02 | 1.0 | 6 | euler_cfg_pp | Flux2Scheduler | 252.0 | Yes | No |
| F-T2I-03 | 1.1 | 6 | euler_cfg_pp | Flux2Scheduler | 220.3 | Yes | Yes |
| F-T2I-04 | 1.2 | 6 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-05 | 1.3 | 6 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-06 | 1.4 | 6 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-07 | 1.5 | 6 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-08 | 1.3 | 6 | euler | Flux2Scheduler | not captured | Yes | No |
| F-T2I-09 | 1.3 | 6 | euler_ancestral | Flux2Scheduler | not captured | Yes | No |
| F-T2I-10 | 1.3 | 6 | euler_ancestral_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-11 | 1.3 | 6 | res_multistep | Flux2Scheduler | not captured | Yes | No |
| F-T2I-12 | 1.3 | 6 | res_multistep_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-13 | 1.3 | 4 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-14 | 1.3 | 5 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-15 | 1.3 | 7 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-16 | 1.3 | 8 | euler_cfg_pp | Flux2Scheduler | not captured | Yes | No |
| F-T2I-17 | 1.3 | 4 | euler_ancestral | Flux2Scheduler | not captured | Yes | No |
| F-T2I-18 | 1.3 | 4 | res_multistep | Flux2Scheduler | not captured | Yes | No |
F-T2I-12 was visually rejected as a corrupted/highly oversaturated output. The remaining completed tests were valid but did not improve on F-T2I-03. Per-test runtimes were not recorded by the collector.
Optional second pass
SeedVR2 3B FP8 produced a successful 2560×1440 output from this baseline. A 3840×2160 attempt ran out of the GPU's 8 GB VRAM. The SeedVR2 pass is therefore an optional export step, not part of the fast generation baseline.