...

https://huggingface.co/Wan-AI/Wan2.1-T2V-14B
Note: 
If you are using the T2V-1.3B model, we recommend setting the parameter --sample_guide_scale 6. 
The --sample_shift parameter can be adjusted within the range of 8 to 12 based on the performance.

Test 0 - Different seed variations

Prompt: Generate a photo of a woman's legs, with her feet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a light gray color. The photo should be taken from a low angle, looking up at the woman's legs. The ribbons should be tied in a bow shape around the ankles. The shoes should have a red sole. The woman's legs should be slightly bent at the knee.

Parameters: Steps: 32| Size: 512x512| Seed: 1620085323| CFG scale: 6| App: SD.Next| Version: 34031f5| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.1-T2V-14B-Diffusers

Time: 9m 23.07s | total 957.28 pipeline 562.74 preview 365.22 offload 12.19 vae 9.25 te 7.82 post 0.30 gc 0.29 | GPU 28016 MB 22% | RAM 40.0 GB 32%

Test 1 - Bookshop

Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling

...

Execution:  Time: 7m 0.68s | total 451.85 pipeline 420.38 offload 11.63 vae 9.38 te 5.40 preview 5.03 post 0.28 gc 0.27 | GPU 28040 MB 22% | RAM 40.38 GB 32%

Test 3 - Legs

Prompt: Create a close-up photograph Generate a photo of a woman's face and handlegs, with her hand raised to her chin. She is wearing a white blazer and has a gold ring on her finger. Her nails are neatly manicured and her hair is pulled back into a low bun. She is smiling and has a radiant expression on her face. The background is a plain light gray color. The overall mood of the photo is elegant and sophisticated. The photo should have a soft, natural light and a slight warmth to it. The woman's hair is dark brown and pulled back into a low bun, with a few loose strands framing her facefeet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a light gray color. The photo should be taken from a low angle, looking up at the woman's legs. The ribbons should be tied in a bow shape around the ankles. The shoes should have a red sole. The woman's legs should be slightly bent at the knee.

Parameters: Steps: 24| Size: 512x512| Seed: 1475741581| CFG scale: 6| App: SD.Next| Version: 287c360| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.1-T2V-14B-Diffusers

Execution: Time: 9m 28.57s | total 605.45 pipeline 560.66 offload 19.51 vae 10.48 move 7.63 te 7.14 post 0.27 gc 0.26 | GPU 29274 MB 23% | RAM 40.42 GB 32%

Test 4 - Different seed variations

Prompt: Generate a photo of a woman's legs, with her feet crossed and wearing white high-heeled shoes with ribbons tied around her ankles. The shoes should have a pointed toe and a stiletto heel. The woman's legs should be smooth and tanned, with a slight sheen to them. The background should be a light gray color. The photo should be taken from a low angle, looking up at the woman's legs. The ribbons should be tied in a bow shape around the ankles. The shoes should have a red sole. The woman's legs should be slightly bent at the knee.

Parameters: Steps: 32| Size: 512x512| Seed: 1620085323| CFG scale: 6| App: SD.Next| Version: 34031f5| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.1-T2V-14B-Diffusers

Time: 9m 23.07s | total 957.28 pipeline 562.74 preview 365.22 offload 12.19 vae 9.25 te 7.82 post 0.30 gc 0.29 | GPU 28016 MB 22% | RAM 40.0 GB 32%

Image Removed

CFG6, STEP 32	Seed: 1620085323	Seed:1931701040	Seed:4075624134	Seed:2736029172
bookshop girl	Image Removed	Image Removed
hand and face	Image Removed	Image Removed	Image Removed	Image Removed
legs and shoes	Image Removed	Image Removed	Image Removed

System info

app: sdnext.git updated: 2025-07-20 hash: 287c3600 url: https://github.com/vladmandic/sdnext.git/tree/dev
arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-24-generic
python: 3.12.3 Torch 2.7.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 
xformers:  diffusers: 0.35.0.dev0 transformers: 4.53.2
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
base: Diffusers/Wan-AI/Wan2.1-T2V-14B-Diffusers [38ec498cb3] refiner: none vae: none te: none unet: none

...

{
  "sd_model_checkpoint": "Diffusers/Wan-AI/Wan2.1-T2V-14B-Diffusers [38ec498cb3]",
  "diffusers_version": "9c13f8657986e68f5f05987912c54432fd28d86f",
  "sd_checkpoint_hash": null,
  "diffusers_offload_min_gpu_memory": 0.05,
  "diffusers_offload_max_gpu_memory": 0.95,
  "diffusers_vae_tiling": true,
  "diffusers_vae_tile_size": 512,
  "dynamic_attention_slice_rate": 1,
  "dynamic_attention_trigger_rate": 2,
  "samples_filename_pattern": "[seq]-[date]-[model_name]-[height]x[width]-STEP[steps]-CFG[cfg]-Seed[seed]"
}

Model info