21 lines
756 B
Markdown
21 lines
756 B
Markdown
# Flux.2 Klein — optimized I2I
|
|
|
|
Converts any supplied reference image into a photorealistic image of the same subject. The prompt is intentionally generic: identity, pose, clothing, accessories, colors, proportions, composition, and framing are inferred from the reference image rather than hard-coded.
|
|
|
|
## Tested baseline
|
|
|
|
- Reference input: `character_reference.png`
|
|
- Model: `flux-2-klein-9b-fp8mixed.safetensors`
|
|
- Text encoder: `qwen_3_8b_fp8mixed.safetensors` (`flux2`)
|
|
- VAE: `full_encoder_small_decoder.safetensors`
|
|
- Sampler: Euler
|
|
- Steps: 4
|
|
- CFG: 1.0
|
|
- Seed: `20260921`
|
|
- Measured runtime: approximately 89 seconds on the RTX 3070
|
|
|
|
Files:
|
|
|
|
- `workflow.json` — API-format prompt.
|
|
- `ui-workflow.json` — native ComfyUI web-editor workflow.
|