Add optimized Qwen Image 2.1 spaceship canteen baseline
This commit is contained in:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user