Add optimized Qwen Image 2.1 spaceship canteen baseline

This commit is contained in:
Morpheus
2026-09-22 17:09:06 +00:00
parent 840072711e
commit a321551449
3 changed files with 833 additions and 0 deletions
@@ -0,0 +1,24 @@
# Qwen Image 2.1 — spaceship canteen baseline
Qwen Image 2.1 text-to-image workflow using the same spaceship-canteen prompt as the Flux.2 Klein baseline.
## Settings
- Model: qwen_image_2.1_int8_convrot.safetensors
- Text encoder: qwen3vl_8b_w4a8.safetensors
- VAE: qwen_image_2.1_vae_bf16.safetensors
- Internal generation: 1024×1024 square (the Qwen 2.1 text encoder provides a square latent)
- Final output: 1920×1088, 16:9, center-cropped with Lanczos
- Sampler: euler_cfg_pp
- Scheduler: simple
- Steps: 12
- CFG: 2.5
- Seed: 20260920
- Warm generation time: approximately 22 seconds on the server RTX 3070
The positive and negative prompts are intentionally identical to the Flux baseline for controlled comparison. The final crop removes the white side bands produced by padding the square Qwen output.
Files:
- workflow.json — API format
- ui-workflow.json — ComfyUI web UI format