Record generation times in test tables

This commit is contained in:
Morpheus
2026-10-28 17:32:04 +00:00
parent 4f08340ea6
commit 6df04c2c6c
7 changed files with 120 additions and 120 deletions
+14 -14
View File
@@ -19,20 +19,20 @@ dimensions, CFG, steps, model, encoder, and scheduler fixed while varying only
the sampler. The local I2I graph uses `Flux2Scheduler`, which does not expose the sampler. The local I2I graph uses `Flux2Scheduler`, which does not expose
the selectable scheduler family used by the T2I `BasicScheduler` matrix. the selectable scheduler family used by the T2I `BasicScheduler` matrix.
| ID | Encoder | Resolution | References | Seed | CFG | Steps | Sampler | Scheduler | Status | Purpose | | ID | Encoder | Resolution | References | Seed | CFG | Steps | Sampler | Scheduler | Generation time (s) | Status | Purpose |
|---|---|---:|---:|---:|---:|---:|---|---|---|---| |---|---|---:|---:|---:|---:|---:|---|---|---:|---|---|
| F3K-I2I-01 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 requested; 1072×1920 actual | 1 | 310101 | 1.0 | 16 | euler | Flux2Scheduler | Completed | Baseline; 16-pixel latent quantization reduced width | | F3K-I2I-01 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 requested; 1072×1920 actual | 1 | 310101 | 1.0 | 16 | euler | Flux2Scheduler | 46.339 | Completed | Baseline; 16-pixel latent quantization reduced width |
| F3K-I2I-02 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | euler_cfg_pp | Flux2Scheduler | Planned | CFG++ comparison | | F3K-I2I-02 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | euler_cfg_pp | Flux2Scheduler | — | Planned | CFG++ comparison |
| F3K-I2I-03 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | euler_ancestral | Flux2Scheduler | Planned | Ancestral comparison | | F3K-I2I-03 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | euler_ancestral | Flux2Scheduler | — | Planned | Ancestral comparison |
| F3K-I2I-04 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | euler_ancestral_cfg_pp | Flux2Scheduler | Planned | Ancestral CFG++ comparison | | F3K-I2I-04 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | euler_ancestral_cfg_pp | Flux2Scheduler | — | Planned | Ancestral CFG++ comparison |
| F3K-I2I-05 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | dpmpp_2m | Flux2Scheduler | Planned | DPM++ comparison | | F3K-I2I-05 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | dpmpp_2m | Flux2Scheduler | — | Planned | DPM++ comparison |
| F3K-I2I-06 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | dpmpp_2m_cfg_pp | Flux2Scheduler | Planned | DPM++ CFG++ comparison | | F3K-I2I-06 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | dpmpp_2m_cfg_pp | Flux2Scheduler | — | Planned | DPM++ CFG++ comparison |
| F3K-I2I-07 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | dpmpp_sde | Flux2Scheduler | Planned | DPM++ SDE comparison | | F3K-I2I-07 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | dpmpp_sde | Flux2Scheduler | — | Planned | DPM++ SDE comparison |
| F3K-I2I-08 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | heun | Flux2Scheduler | Planned | Heun comparison | | F3K-I2I-08 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | heun | Flux2Scheduler | — | Planned | Heun comparison |
| F3K-I2I-09 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | res_multistep | Flux2Scheduler | Planned | RES multistep comparison | | F3K-I2I-09 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | res_multistep | Flux2Scheduler | — | Planned | RES multistep comparison |
| F3K-I2I-10 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | res_multistep_cfg_pp | Flux2Scheduler | Planned | RES multistep CFG++ comparison | | F3K-I2I-10 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | res_multistep_cfg_pp | Flux2Scheduler | — | Planned | RES multistep CFG++ comparison |
| F3K-I2I-11 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | ddim | Flux2Scheduler | Planned | DDIM comparison | | F3K-I2I-11 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | ddim | Flux2Scheduler | — | Planned | DDIM comparison |
| F3K-I2I-12 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | uni_pc | Flux2Scheduler | Planned | UniPC comparison | | F3K-I2I-12 | `qwen3-vl-4b-heretic_int8.safetensors` | 1080×1920 | 1 | 310101 | 1.0 | 16 | uni_pc | Flux2Scheduler | — | Planned | UniPC comparison |
Use `../character_reference.png`, the canonical I2I prompt, and the installed Use `../character_reference.png`, the canonical I2I prompt, and the installed
`flux3-image-klein-int8-convrot.safetensors`. Record the reference path/hash, `flux3-image-klein-int8-convrot.safetensors`. Record the reference path/hash,
+14 -14
View File
@@ -19,20 +19,20 @@ seed, dimensions, CFG, steps, model, encoder, and scheduler fixed while
varying only the sampler. The submitted baseline overrides the source graph to 16 steps with varying only the sampler. The submitted baseline overrides the source graph to 16 steps with
`Flux2Scheduler`. `Flux2Scheduler`.
| ID | Encoder | Resolution | References | Seed | CFG | Steps | Sampler | Scheduler | Status | Purpose | | ID | Encoder | Resolution | References | Seed | CFG | Steps | Sampler | Scheduler | Generation time (s) | Status | Purpose |
|---|---|---:|---:|---:|---:|---:|---|---|---|---| |---|---|---:|---:|---:|---:|---:|---|---|---:|---|---|
| F3K-MI2I-01 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 requested; 1920×1072 actual | 2 | 310101 | 1.0 | 16 | euler | Flux2Scheduler | Completed | Baseline; 16-pixel latent quantization reduced height | | F3K-MI2I-01 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 requested; 1920×1072 actual | 2 | 310101 | 1.0 | 16 | euler | Flux2Scheduler | 59.115 | Completed | Baseline; 16-pixel latent quantization reduced height |
| F3K-MI2I-02 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | euler_cfg_pp | Flux2Scheduler | Planned | CFG++ comparison | | F3K-MI2I-02 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | euler_cfg_pp | Flux2Scheduler | — | Planned | CFG++ comparison |
| F3K-MI2I-03 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | euler_ancestral | Flux2Scheduler | Planned | Ancestral comparison | | F3K-MI2I-03 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | euler_ancestral | Flux2Scheduler | — | Planned | Ancestral comparison |
| F3K-MI2I-04 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | euler_ancestral_cfg_pp | Flux2Scheduler | Planned | Ancestral CFG++ comparison | | F3K-MI2I-04 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | euler_ancestral_cfg_pp | Flux2Scheduler | — | Planned | Ancestral CFG++ comparison |
| F3K-MI2I-05 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | dpmpp_2m | Flux2Scheduler | Planned | DPM++ comparison | | F3K-MI2I-05 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | dpmpp_2m | Flux2Scheduler | — | Planned | DPM++ comparison |
| F3K-MI2I-06 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | dpmpp_2m_cfg_pp | Flux2Scheduler | Planned | DPM++ CFG++ comparison | | F3K-MI2I-06 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | dpmpp_2m_cfg_pp | Flux2Scheduler | — | Planned | DPM++ CFG++ comparison |
| F3K-MI2I-07 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | dpmpp_sde | Flux2Scheduler | Planned | DPM++ SDE comparison | | F3K-MI2I-07 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | dpmpp_sde | Flux2Scheduler | — | Planned | DPM++ SDE comparison |
| F3K-MI2I-08 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | heun | Flux2Scheduler | Planned | Heun comparison | | F3K-MI2I-08 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | heun | Flux2Scheduler | — | Planned | Heun comparison |
| F3K-MI2I-09 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | res_multistep | Flux2Scheduler | Planned | RES multistep comparison | | F3K-MI2I-09 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | res_multistep | Flux2Scheduler | — | Planned | RES multistep comparison |
| F3K-MI2I-10 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | res_multistep_cfg_pp | Flux2Scheduler | Planned | RES multistep CFG++ comparison | | F3K-MI2I-10 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | res_multistep_cfg_pp | Flux2Scheduler | — | Planned | RES multistep CFG++ comparison |
| F3K-MI2I-11 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | ddim | Flux2Scheduler | Planned | DDIM comparison | | F3K-MI2I-11 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | ddim | Flux2Scheduler | — | Planned | DDIM comparison |
| F3K-MI2I-12 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | uni_pc | Flux2Scheduler | Planned | UniPC comparison | | F3K-MI2I-12 | `qwen3-vl-4b-heretic_int8.safetensors` | 1920×1080 | 2 | 310101 | 1.0 | 16 | uni_pc | Flux2Scheduler | — | Planned | UniPC comparison |
Use both canonical reference images, the shared MultipleRef2I prompt, and the Use both canonical reference images, the shared MultipleRef2I prompt, and the
installed `flux3-image-klein-int8-convrot.safetensors`. Record both reference installed `flux3-image-klein-int8-convrot.safetensors`. Record both reference
+20 -20
View File
@@ -24,26 +24,26 @@ All 18 rows are currently **Planned**. Keep both references, the prompt,
resolution, and seed fixed; vary only the explicitly listed CFG, sampler, resolution, and seed fixed; vary only the explicitly listed CFG, sampler,
scheduler, or steps. scheduler, or steps.
| ID | CFG | Steps | Sampler | Scheduler | Status | Purpose | | ID | CFG | Steps | Sampler | Scheduler | Generation time (s) | Status | Purpose |
|---|---:|---:|---|---|---|---| |---|---:|---:|---|---|---:|---|---|
| Q-MR2I-01 | 3.5 | 50 | euler_cfg_pp | beta | Planned | Baseline | | Q-MR2I-01 | 3.5 | 50 | euler_cfg_pp | beta | — | Planned | Baseline |
| Q-MR2I-02 | 1.0 | 24 | euler_cfg_pp | beta | Planned | Low CFG | | Q-MR2I-02 | 1.0 | 24 | euler_cfg_pp | beta | — | Planned | Low CFG |
| Q-MR2I-03 | 2.5 | 24 | euler_cfg_pp | beta | Planned | CFG comparison | | Q-MR2I-03 | 2.5 | 24 | euler_cfg_pp | beta | — | Planned | CFG comparison |
| Q-MR2I-04 | 3.5 | 24 | euler_cfg_pp | beta | Planned | CFG/steps comparison | | Q-MR2I-04 | 3.5 | 24 | euler_cfg_pp | beta | — | Planned | CFG/steps comparison |
| Q-MR2I-05 | 4.0 | 24 | euler_cfg_pp | beta | Planned | Higher CFG | | Q-MR2I-05 | 4.0 | 24 | euler_cfg_pp | beta | — | Planned | Higher CFG |
| Q-MR2I-06 | 3.5 | 24 | euler | beta | Planned | Euler sampler | | Q-MR2I-06 | 3.5 | 24 | euler | beta | — | Planned | Euler sampler |
| Q-MR2I-07 | 3.5 | 24 | euler_ancestral | beta | Planned | Ancestral sampler | | Q-MR2I-07 | 3.5 | 24 | euler_ancestral | beta | — | Planned | Ancestral sampler |
| Q-MR2I-08 | 3.5 | 24 | res_multistep | beta | Planned | RES sampler | | Q-MR2I-08 | 3.5 | 24 | res_multistep | beta | — | Planned | RES sampler |
| Q-MR2I-09 | 3.5 | 24 | res_multistep_cfg_pp | beta | Planned | RES CFG++ sampler | | Q-MR2I-09 | 3.5 | 24 | res_multistep_cfg_pp | beta | — | Planned | RES CFG++ sampler |
| Q-MR2I-10 | 2.5 | 24 | euler_cfg_pp | simple | Planned | Scheduler comparison | | Q-MR2I-10 | 2.5 | 24 | euler_cfg_pp | simple | — | Planned | Scheduler comparison |
| Q-MR2I-11 | 2.5 | 24 | euler_cfg_pp | sgm_uniform | Planned | Scheduler comparison | | Q-MR2I-11 | 2.5 | 24 | euler_cfg_pp | sgm_uniform | — | Planned | Scheduler comparison |
| Q-MR2I-12 | 2.5 | 24 | euler_cfg_pp | karras | Planned | Scheduler comparison | | Q-MR2I-12 | 2.5 | 24 | euler_cfg_pp | karras | — | Planned | Scheduler comparison |
| Q-MR2I-13 | 2.5 | 24 | euler_cfg_pp | exponential | Planned | Scheduler comparison | | Q-MR2I-13 | 2.5 | 24 | euler_cfg_pp | exponential | — | Planned | Scheduler comparison |
| Q-MR2I-14 | 3.5 | 30 | euler_cfg_pp | beta | Planned | Step-count comparison | | Q-MR2I-14 | 3.5 | 30 | euler_cfg_pp | beta | — | Planned | Step-count comparison |
| Q-MR2I-15 | 3.5 | 40 | euler_cfg_pp | beta | Planned | Step-count comparison | | Q-MR2I-15 | 3.5 | 40 | euler_cfg_pp | beta | — | Planned | Step-count comparison |
| Q-MR2I-16 | 3.5 | 60 | euler_cfg_pp | beta | Planned | Step-count comparison | | Q-MR2I-16 | 3.5 | 60 | euler_cfg_pp | beta | — | Planned | Step-count comparison |
| Q-MR2I-17 | 3.5 | 75 | euler_cfg_pp | beta | Planned | Step-count comparison | | Q-MR2I-17 | 3.5 | 75 | euler_cfg_pp | beta | — | Planned | Step-count comparison |
| Q-MR2I-18 | 3.5 | 50 | euler_ancestral | beta | Planned | Baseline sampler alternative | | Q-MR2I-18 | 3.5 | 50 | euler_ancestral | beta | — | Planned | Baseline sampler alternative |
Record both reference hashes, runtime, output dimensions/path, exact settings, Record both reference hashes, runtime, output dimensions/path, exact settings,
and visual notes for every run. Do not reduce the reference count silently if and visual notes for every run. Do not reduce the reference count silently if
+31 -31
View File
@@ -79,37 +79,37 @@ explicit structural bypass: the sampler, scheduler, second pass, and decode
path connect directly to the LoRA/model output rather than relying only on path connect directly to the LoRA/model output rather than relying only on
Spectrum's `enabled=false` switch. Spectrum's `enabled=false` switch.
| ID | Workflow | Prompt | Chunks × seconds | Target | Status | Result | | ID | Workflow | Prompt | Chunks × seconds | Target | Generation time (s) | Status | Result |
|---|---|---|---:|---:|---|---| |---|---|---|---:|---:|---:|---|---|
| CT-01 | Spectrum graph | Compact | 2 × 4 | 8s configured | **Completed** | 17m 49.959s render; expected 4.0s output, 1920×1088, 96 frames | | CT-01 | Spectrum graph | Compact | 2 × 4 | 8s configured | 1069.959 | **Completed** | Expected 4.0s output, 1920×1088, 96 frames |
| CT-02 | Spectrum + EasyCache + clear VRAM | Detailed continuity | 2 × 4 | 8s configured | **Completed** | 21m 49.127s render; expected 4.0s output, 1920×1088, 96 frames | | CT-02 | Spectrum + EasyCache + clear VRAM | Detailed continuity | 2 × 4 | 8s configured | 1309.127 | **Completed** | Expected 4.0s output, 1920×1088, 96 frames |
| CT-03 | Spectrum + EasyCache + clear VRAM | Cinematic camera | 2 × 4 | 8s configured | **Completed** | 22m 50.266s render; expected 4.0s output, 1920×1088, 96 frames | | CT-03 | Spectrum + EasyCache + clear VRAM | Cinematic camera | 2 × 4 | 8s configured | 1370.266 | **Completed** | Expected 4.0s output, 1920×1088, 96 frames |
| CT-04 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 3 × 4 | 12s | **Completed** | 71m 39.693s render; 12.0s output, 1920×1088, 288 frames; 3/3 chunks | | CT-04 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 3 × 4 | 12s | 4299.693 | **Completed** | 12.0s output, 1920×1088, 288 frames; 3/3 chunks |
| CT-05 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 4 × 4 | 16s | **Lost** | Prompt absent from queue and history; no output available | | CT-05 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 4 × 4 | 16s | — | **Lost** | Prompt absent from queue and history; no output available |
| CT-06 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 5 × 4 | 20s | **Completed** | 121m 47.263s; 20.0s output, 1920×1088, 480 frames; 5/5 chunks | | CT-06 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 5 × 4 | 20s | 7307.263 | **Completed** | 20.0s output, 1920×1088, 480 frames; 5/5 chunks |
| CT-07 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 6 × 5.17 (124 frames) | 31.02s | Planned | — | | CT-07 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 6 × 5.17 (124 frames) | 31.02s | — | Planned | — |
| CT-08 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 7 × 7.29 (175 frames) | 51.03s | Planned | — | | CT-08 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 7 × 7.29 (175 frames) | 51.03s | — | Planned | — |
| CT-09 | Spectrum + EasyCache + clear VRAM | Longform 30s | 6 × 10.13 (243 frames) | 60.78s | Planned | — | | CT-09 | Spectrum + EasyCache + clear VRAM | Longform 30s | 6 × 10.13 (243 frames) | 60.78s | — | Planned | — |
| CT-B01 | Spectrum bypassed | Compact | 2 × 4 | 8s configured | **Completed** | 16m 42.576s render; 4.0s output, 1920×1088, 24 fps, 96 frames; 1/2 logical chunks emitted | | CT-B01 | Spectrum bypassed | Compact | 2 × 4 | 8s configured | 1002.576 | **Completed** | 4.0s output, 1920×1088, 24 fps, 96 frames; 1/2 logical chunks emitted |
| CT-B02 | Bypassed + EasyCache + clear VRAM | Detailed continuity | 2 × 3.75 (90 frames) | 7.5s | Planned | — | | CT-B02 | Bypassed + EasyCache + clear VRAM | Detailed continuity | 2 × 3.75 (90 frames) | 7.5s | — | Planned | — |
| CT-B03 | Bypassed + EasyCache + clear VRAM | Cinematic camera | 2 × 3.75 (90 frames) | 7.5s | Planned | — | | CT-B03 | Bypassed + EasyCache + clear VRAM | Cinematic camera | 2 × 3.75 (90 frames) | 7.5s | — | Planned | — |
| CT-B04 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 3 × 5.17 (124 frames) | 15.51s | Planned | — | | CT-B04 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 3 × 5.17 (124 frames) | 15.51s | — | Planned | — |
| CT-B05 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 4 × 5.17 (124 frames) | 20.68s | Planned | — | | CT-B05 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 4 × 5.17 (124 frames) | 20.68s | — | Planned | — |
| CT-B06 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 5 × 5.17 (124 frames) | 25.85s | Planned | — | | CT-B06 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 5 × 5.17 (124 frames) | 25.85s | — | Planned | — |
| CT-B07 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 6 × 5.17 (124 frames) | 31.02s | Planned | — | | CT-B07 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 6 × 5.17 (124 frames) | 31.02s | — | Planned | — |
| CT-B08 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 7 × 5.17 (124 frames) | 36.19s | Planned | — | | CT-B08 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 7 × 5.17 (124 frames) | 36.19s | — | Planned | — |
| CT-B09 | Bypassed + EasyCache + clear VRAM | Longform 30s | 6 × 7.29 (175 frames) | 43.74s | Planned | — | | CT-B09 | Bypassed + EasyCache + clear VRAM | Longform 30s | 6 × 7.29 (175 frames) | 43.74s | — | Planned | — |
| CT-10 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 3.75 (90 frames) | 7.5s | Planned | — | | CT-10 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 3.75 (90 frames) | 7.5s | — | Planned | — |
| CT-11 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 5.17 (124 frames) | 10.34s | Planned | — | | CT-11 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 5.17 (124 frames) | 10.34s | — | Planned | — |
| CT-12 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 7.29 (175 frames) | 14.58s | Planned | — | | CT-12 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 7.29 (175 frames) | 14.58s | — | Planned | — |
| CT-13 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 10.13 (243 frames) | 20.26s | **Completed** | 80m 30.304s; 20.25s output, 1920×1088, 486 frames; 2/2 chunks | | CT-13 | Spectrum + EasyCache + clear VRAM | Best smoke prompt | 2 × 10.13 (243 frames) | 20.26s | 4830.304 | **Completed** | 20.25s output, 1920×1088, 486 frames; 2/2 chunks |
| CT-14 | Spectrum + EasyCache + clear VRAM | Four 243-frame chunks | 4 × 10.13 (243 frames) | 40.52s | **Lost** | Prompt absent from ComfyUI queue and history; no output available; no duplicate submission made | | CT-14 | Spectrum + EasyCache + clear VRAM | Four 243-frame chunks | 4 × 10.13 (243 frames) | 40.52s | — | **Lost** | Prompt absent from ComfyUI queue and history; no output available; no duplicate submission made |
| CT-B10 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 3.75 (90 frames) | 7.5s | Planned | — | | CT-B10 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 3.75 (90 frames) | 7.5s | — | Planned | — |
| CT-B11 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 5.17 (124 frames) | 10.34s | Planned | — | | CT-B11 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 5.17 (124 frames) | 10.34s | — | Planned | — |
| CT-B12 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 7.29 (175 frames) | 14.58s | Planned | — | | CT-B12 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 7.29 (175 frames) | 14.58s | — | Planned | — |
| CT-B13 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 10.13 (243 frames) | 20.26s | Planned | — | | CT-B13 | Bypassed + EasyCache + clear VRAM | Best smoke prompt | 2 × 10.13 (243 frames) | 20.26s | — | Planned | — |
| CT-B14 | Bypassed + EasyCache + clear VRAM | Longform 30s | 2 × 15.08 (362 frames) | 30.16s | Planned | — | | CT-B14 | Bypassed + EasyCache + clear VRAM | Longform 30s | 2 × 15.08 (362 frames) | 30.16s | — | Planned | — |
| CT-15 | Spectrum + EasyCache + clear VRAM | 226-frame chunks | 2 × 9.4 | 18.8s | **Lost** | Prompt absent from history and queue; no output available | | CT-15 | Spectrum + EasyCache + clear VRAM | 226-frame chunks | 2 × 9.4 | 18.8s | — | **Lost** | Prompt absent from history and queue; no output available |
The CT-10–CT-14 sweep isolates individual chunk length: it holds the chunk The CT-10–CT-14 sweep isolates individual chunk length: it holds the chunk
count at two and uses the valid maximum-frame choices 90, 124, 175, 243, and count at two and uses the valid maximum-frame choices 90, 124, 175, 243, and
@@ -42,12 +42,12 @@ Every test changes only the listed variables. Record runtime, peak VRAM, success
### Phase A — Upscale ceiling ### Phase A — Upscale ceiling
| ID | Initial latent | Target latent | Tile | Purpose | | ID | Initial latent | Target latent | Tile | Generation time (s) | Purpose |
|---|---:|---:|---:|---| |---|---:|---:|---|---:|---|
| SLU-01 | 672×384 | 1344×768 | supplied baseline tile | Reproduce the supplied good result | | SLU-01 | 672×384 | 1344×768 | supplied baseline tile | — | Reproduce the supplied good result |
| SLU-02 | 672×384 | 1920×1080 | supplied baseline tile | Test the desired 1080p endpoint | | SLU-02 | 672×384 | 1920×1080 | supplied baseline tile | — | Test the desired 1080p endpoint |
| SLU-03 | 672×384 | 1680×960 | supplied baseline tile | Intermediate fallback if 1080p fails or is too slow | | SLU-03 | 672×384 | 1680×960 | supplied baseline tile | — | Intermediate fallback if 1080p fails or is too slow |
| SLU-04 | 672×384 | 1536×864 | supplied baseline tile | Practical quality/runtime fallback | | SLU-04 | 672×384 | 1536×864 | supplied baseline tile | — | Practical quality/runtime fallback |
### Phase B — Tile size ### Phase B — Tile size
+20 -20
View File
@@ -31,26 +31,26 @@ scheduler, and reference count stay fixed while sampler varies.
This follows the practical 18-row scope used by the Flux.2 Klein plan: focused This follows the practical 18-row scope used by the Flux.2 Klein plan: focused
sampler comparisons with the standard settings held constant. The remaining rows are currently **Planned**. sampler comparisons with the standard settings held constant. The remaining rows are currently **Planned**.
| ID | Guidance | Steps | Sampler | Scheduler | Status | Purpose | | ID | Guidance | Steps | Sampler | Scheduler | Generation time (s) | Status | Purpose |
|---|---:|---:|---|---|---|---| |---|---:|---:|---|---|---:|---|---|
| F3I-T2I-01 | 1.0 | 16 | euler | simple | Failed (validation) | Baseline; requested encoder absent | | F3I-T2I-01 | 1.0 | 16 | euler | simple | — | Failed (validation) | Baseline; requested encoder absent |
| F3I-T2I-02 | 1.0 | 16 | euler_cfg_pp | simple | Planned | CFG++ sampler | | F3I-T2I-02 | 1.0 | 16 | euler_cfg_pp | simple | — | Planned | CFG++ sampler |
| F3I-T2I-03 | 1.0 | 16 | euler_ancestral | simple | Planned | Ancestral sampler | | F3I-T2I-03 | 1.0 | 16 | euler_ancestral | simple | — | Planned | Ancestral sampler |
| F3I-T2I-04 | 1.0 | 16 | euler_ancestral_cfg_pp | simple | Planned | Ancestral CFG++ sampler | | F3I-T2I-04 | 1.0 | 16 | euler_ancestral_cfg_pp | simple | — | Planned | Ancestral CFG++ sampler |
| F3I-T2I-05 | 1.0 | 16 | res_multistep | simple | Planned | RES multistep sampler | | F3I-T2I-05 | 1.0 | 16 | res_multistep | simple | — | Planned | RES multistep sampler |
| F3I-T2I-06 | 1.0 | 16 | res_multistep_cfg_pp | simple | Planned | RES multistep CFG++ sampler | | F3I-T2I-06 | 1.0 | 16 | res_multistep_cfg_pp | simple | — | Planned | RES multistep CFG++ sampler |
| F3I-T2I-07 | 1.0 | 16 | dpmpp_2m | simple | Planned | DPM++ sampler | | F3I-T2I-07 | 1.0 | 16 | dpmpp_2m | simple | — | Planned | DPM++ sampler |
| F3I-T2I-08 | 1.0 | 16 | ddim | simple | Planned | DDIM sampler | | F3I-T2I-08 | 1.0 | 16 | ddim | simple | — | Planned | DDIM sampler |
| F3I-T2I-09 | 1.0 | 16 | uni_pc | simple | Planned | UniPC sampler | | F3I-T2I-09 | 1.0 | 16 | uni_pc | simple | — | Planned | UniPC sampler |
| F3I-T2I-10 | 1.0 | 16 | heun | simple | Planned | Heun sampler | | F3I-T2I-10 | 1.0 | 16 | heun | simple | — | Planned | Heun sampler |
| F3I-T2I-11 | 1.0 | 16 | dpmpp_sde | simple | Planned | DPM++ SDE sampler | | F3I-T2I-11 | 1.0 | 16 | dpmpp_sde | simple | — | Planned | DPM++ SDE sampler |
| F3I-T2I-12 | 1.0 | 16 | dpmpp_2m_cfg_pp | simple | Planned | DPM++ CFG++ sampler | | F3I-T2I-12 | 1.0 | 16 | dpmpp_2m_cfg_pp | simple | — | Planned | DPM++ CFG++ sampler |
| F3I-T2I-13 | 1.0 | 16 | lcm | simple | Planned | LCM sampler | | F3I-T2I-13 | 1.0 | 16 | lcm | simple | — | Planned | LCM sampler |
| F3I-T2I-14 | 1.0 | 16 | deis | simple | Planned | DEIS sampler | | F3I-T2I-14 | 1.0 | 16 | deis | simple | — | Planned | DEIS sampler |
| F3I-T2I-15 | 1.0 | 16 | ipndm | simple | Planned | IPNDM sampler | | F3I-T2I-15 | 1.0 | 16 | ipndm | simple | — | Planned | IPNDM sampler |
| F3I-T2I-16 | 1.0 | 16 | sa_solver | simple | Planned | SA solver | | F3I-T2I-16 | 1.0 | 16 | sa_solver | simple | — | Planned | SA solver |
| F3I-T2I-17 | 1.0 | 16 | uni_pc_bh2 | simple | Planned | UniPC BH2 sampler | | F3I-T2I-17 | 1.0 | 16 | uni_pc_bh2 | simple | — | Planned | UniPC BH2 sampler |
| F3I-T2I-18 | 1.0 | 16 | gradient_estimation | simple | Planned | Gradient-estimation sampler | | F3I-T2I-18 | 1.0 | 16 | gradient_estimation | simple | — | Planned | Gradient-estimation sampler |
Record runtime, output dimensions, output path, exact settings, and visual Record runtime, output dimensions, output path, exact settings, and visual
notes for every row under `results/`. Record failures rather than silently notes for every row under `results/`. Record failures rather than silently
+15 -15
View File
@@ -61,10 +61,10 @@ fine-tuning details should not be treated as verified claims.
The first smoke tests use the same 512×512 structured caption and seed before The first smoke tests use the same 512×512 structured caption and seed before
full-size tests are queued. Exact prompt IDs are recorded in `smoke-tests.json`. full-size tests are queued. Exact prompt IDs are recorded in `smoke-tests.json`.
| ID | Model | Steps | Sampler | Scheduler | Shift | CFG | Status | | ID | Model | Steps | Sampler | Scheduler | Shift | CFG | Generation time (s) | Status |
|---|---|---:|---|---|---:|---:|---| |---|---|---:|---|---|---:|---:|---:|---|
| IDEO-SMOKE-FAL-10 | Fal Ideogram | 10 | Euler | simple | 5.25 | 1 | Complete | | IDEO-SMOKE-FAL-10 | Fal Ideogram | 10 | Euler | simple | 5.25 | 1 | 45.483 | Complete |
| IDEO-SMOKE-LOCAL-08 | Local Ideogram | 8 | Euler | simple | 5.25 | 1 | Complete | | IDEO-SMOKE-LOCAL-08 | Local Ideogram | 8 | Euler | simple | 5.25 | 1 | 29.268 | Complete |
Smoke results: both completed without node errors. Fal took 45.483 seconds and Smoke results: both completed without node errors. Fal took 45.483 seconds and
was visually strong. Local took 29.268 seconds and was coherent but notably was visually strong. Local took 29.268 seconds and was coherent but notably
@@ -81,17 +81,17 @@ Keep the prompt and seed fixed for sampler tests. Keep all other settings fixed
when changing one variable. A row is not promoted until detail, anatomy, when changing one variable. A row is not promoted until detail, anatomy,
composition, text fidelity, artefacts, and runtime are reviewed. composition, text fidelity, artefacts, and runtime are reviewed.
| ID | Model | Resolution | Steps | Sampler | Scheduler | Shift | CFG | Purpose | Status | | ID | Model | Resolution | Steps | Sampler | Scheduler | Shift | CFG | Generation time (s) | Purpose | Status |
|---|---|---:|---:|---|---|---:|---:|---|---| |---|---|---:|---:|---|---|---:|---:|---:|---|---|
| IDEO-AUTHOR-01 | Fal | 768×1024 | 8 | Euler | simple | 5.25 | 1 | Author sampling | Complete | | IDEO-AUTHOR-01 | Fal | 768×1024 | 8 | Euler | simple | 5.25 | 1 | — | Author sampling | Complete |
| IDEO-AUTHOR-02 | Fal | 768×1024 | 8 | Euler | simple | 5.25 | 1 | Fal author sampling | Complete | | IDEO-AUTHOR-02 | Fal | 768×1024 | 8 | Euler | simple | 5.25 | 1 | — | Fal author sampling | Complete |
| IDEO-CARD-10 | Fal | 768×1024 | 10 | Euler | simple | 5.25 | 1 | Model-card step count | Complete | | IDEO-CARD-10 | Fal | 768×1024 | 10 | Euler | simple | 5.25 | 1 | — | Model-card step count | Complete |
| IDEO-SAMPLER-01 | Fal | 768×1024 | 8 | res_multistep | simple | 5.25 | 1 | Sampler comparison | Complete | | IDEO-SAMPLER-01 | Fal | 768×1024 | 8 | res_multistep | simple | 5.25 | 1 | — | Sampler comparison | Complete |
| IDEO-SAMPLER-02 | Fal | 768×1024 | 8 | euler_ancestral | simple | 5.25 | 1 | Sampler comparison | Complete | | IDEO-SAMPLER-02 | Fal | 768×1024 | 8 | euler_ancestral | simple | 5.25 | 1 | — | Sampler comparison | Complete |
| IDEO-SCHED-01 | Fal | 768×1024 | 8 | Euler | beta | 5.25 | 1 | Scheduler comparison | Complete | | IDEO-SCHED-01 | Fal | 768×1024 | 8 | Euler | beta | 5.25 | 1 | — | Scheduler comparison | Complete |
| IDEO-SHIFT-01 | Fal | 768×1024 | 8 | Euler | simple | 3.0 | 1 | Shift comparison | Complete | | IDEO-SHIFT-01 | Fal | 768×1024 | 8 | Euler | simple | 3.0 | 1 | — | Shift comparison | Complete |
| IDEO-SHIFT-02 | Fal | 768×1024 | 8 | Euler | simple | 7.0 | 1 | Shift comparison | Complete | | IDEO-SHIFT-02 | Fal | 768×1024 | 8 | Euler | simple | 7.0 | 1 | — | Shift comparison | Complete |
| IDEO-STEPS-01 | Fal | 768×1024 | 6 | Euler | simple | 5.25 | 1 | Speed lower bound | Complete | | IDEO-STEPS-01 | Fal | 768×1024 | 6 | Euler | simple | 5.25 | 1 | — | Speed lower bound | Complete |
Quality ranking: `IDEO-CARD-10`, `IDEO-SCHED-01`, `IDEO-SHIFT-02`, Quality ranking: `IDEO-CARD-10`, `IDEO-SCHED-01`, `IDEO-SHIFT-02`,
`IDEO-AUTHOR-02`, `IDEO-AUTHOR-01`, `IDEO-SAMPLER-02`, `IDEO-STEPS-01`, `IDEO-AUTHOR-02`, `IDEO-AUTHOR-01`, `IDEO-SAMPLER-02`, `IDEO-STEPS-01`,