54 lines
2.8 KiB
Markdown
54 lines
2.8 KiB
Markdown
# Qwen Image 2.1 — optimized I2I
|
||
|
||
Converts any supplied reference image into a photorealistic image of the same subject. The prompt is generic: identity, pose, clothing, accessories, colors, proportions, composition, and framing are inferred from the input rather than hard-coded.
|
||
|
||
## Reusable inputs
|
||
|
||
- `character_reference.png` in node `4` — replace with the reference image.
|
||
- Node `7` positive and negative prompts — adapt the transformation without describing a specific subject.
|
||
- Node `10` seed — change for alternate results or keep fixed for comparisons.
|
||
- Nodes `5` and `14` — change the generation and output dimensions. The default is portrait 1080×1920 for person-focused images.
|
||
|
||
## Optimization baseline
|
||
|
||
- Model: `qwen_image_2.1_int8_convrot.safetensors`
|
||
- Sampler: Euler CFG++
|
||
- Scheduler: beta
|
||
- Steps: 40
|
||
- CFG: 3.5
|
||
- Measured runtime: approximately 81 seconds on the RTX 3070
|
||
|
||
The workflow uses the installed Qwen Image 2.1 stack and the flattened `images.image_1` reference input required by the API workflow.
|
||
|
||
- `workflow.json` — API-format workflow.
|
||
|
||
### Expanded sweep plan
|
||
|
||
The next sweep should use the same reference asset and dimensions while covering finer CFG values, more samplers, and scheduler alternatives. Every row remains **Untested**.
|
||
|
||
| Sweep | CFG values | Steps | Samplers | Schedulers | Tested? |
|
||
|---|---|---:|---|---|---|
|
||
| Q-I2I-CFG-low | 1.0, 1.1, 1.2, 1.3, 1.4, 1.5 | 24 | euler_cfg_pp | simple, beta | No |
|
||
| Q-I2I-CFG-mid | 1.6, 1.8, 2.0, 2.2, 2.4, 2.5 | 24 | euler_cfg_pp | simple, beta | No |
|
||
| Q-I2I-CFG-high | 2.5, 2.7, 3.0, 3.2, 3.5, 3.8, 4.0 | 24 | euler_cfg_pp | beta | No |
|
||
| Q-I2I-ancestral | 1.5, 2.0, 2.5, 3.0, 3.5 | 24, 30, 40 | euler_ancestral, euler_ancestral_cfg_pp | beta | No |
|
||
| Q-I2I-res | 1.5, 2.0, 2.5, 3.0, 3.5 | 24, 30, 40 | res_multistep, res_multistep_cfg_pp, res_multistep_ancestral, res_multistep_ancestral_cfg_pp | beta | No |
|
||
| Q-I2I-schedulers | 2.5, 3.0, 3.5 | 24, 40 | euler_cfg_pp | simple, beta, sgm_uniform, karras, exponential, normal | No |
|
||
|
||
## Planned optimization matrix
|
||
|
||
All rows are intentionally **Untested**. Keep the reference image, prompt, seed, and dimensions from [`../variables.json`](../variables.json) fixed.
|
||
|
||
| ID | CFG | Steps | Sampler | Scheduler | Tested? |
|
||
|---|---:|---:|---|---|---|
|
||
| Q-I2I-01 baseline | 3.5 | 40 | euler_cfg_pp | beta | No |
|
||
| Q-I2I-02 | 2.5 | 24 | euler_cfg_pp | beta | No |
|
||
| Q-I2I-03 | 2.5 | 30 | euler_cfg_pp | beta | No |
|
||
| Q-I2I-04 | 2.5 | 40 | euler_cfg_pp | beta | No |
|
||
| Q-I2I-05 | 3.5 | 40 | euler | beta | No |
|
||
| Q-I2I-06 | 3.5 | 40 | res_multistep | beta | No |
|
||
| Q-I2I-07 | 3.0 | 30 | euler_cfg_pp | simple | No |
|
||
| Q-I2I-08 | 4.0 | 30 | euler_cfg_pp | beta | No |
|
||
| Q-I2I-09 | 3.5 | 50 | euler_cfg_pp | beta | No |
|
||
| Q-I2I-10 | 3.5 | 40 | euler_cfg_pp | sgm_uniform | No |
|