Info
| high noice | low noise | combined | |
|---|---|---|---|
WAN 2.2. A14B 512px |
Prompt: A woman with long flowing hair and a sleek black dress silhouette dances gracefully in front of a large floor-to-ceiling window, her movements fluid and expressive. The window reveals a breathtaking panoramic view of a sprawling winter city at night, snow-covered rooftops gleam beneath dim streetlights, neon signs flicker across icy facades, and distant bridges reflect shimmering lights on frozen rivers. Frost patterns adorn the glass, adding depth and realism to the scene. Above the dancer, image wide bold red text reads "WAN 2.2"; smaller black text in a cyan circle "14B" appears in the upper-left corner, subtly indicating version information. The overall mood is serene yet dynamic, blending elegance with urban coldness, illuminated by warm contrasts between the dancer’s motion and the stark beauty of the nighttime landscape. Parameters: Steps: 20| Size: 512x512| Seed: 324| CFG scale: 6| App: SD.Next| Version: 6ea881b| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-T2V-A14B-Diffusers Time: 2m 23.23s | total 191.41 pipeline 143.20 preview 45.54 te 1.49 vae 1.15 | GPU 39818 MB 32% | RAM 42.71 GB 35% |
Prompt: A woman with long flowing hair and a sleek black dress silhouette dances gracefully in front of a large floor-to-ceiling window, her movements fluid and expressive. The window reveals a breathtaking panoramic view of a sprawling winter city at night, snow-covered rooftops gleam beneath dim streetlights, neon signs flicker across icy facades, and distant bridges reflect shimmering lights on frozen rivers. Frost patterns adorn the glass, adding depth and realism to the scene. Above the dancer, image wide bold red text reads "WAN 2.2"; smaller black text in a cyan circle "14B" appears in the upper-left corner, subtly indicating version information. The overall mood is serene yet dynamic, blending elegance with urban coldness, illuminated by warm contrasts between the dancer’s motion and the stark beauty of the nighttime landscape. Parameters: Steps: 20| Size: 512x512| Seed: 324| CFG scale: 6| App: SD.Next| Version: 6ea881b| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-T2V-A14B-Diffusers Time: 2m 32.26s | total 207.77 pipeline 152.19 preview 51.21 te 2.95 vae 1.36 | GPU 39880 MB 32% | RAM 43.8 GB 36% |
Prompt: A woman with long flowing hair and a sleek black dress silhouette dances gracefully in front of a large floor-to-ceiling window, her movements fluid and expressive. The window reveals a breathtaking panoramic view of a sprawling winter city at night, snow-covered rooftops gleam beneath dim streetlights, neon signs flicker across icy facades, and distant bridges reflect shimmering lights on frozen rivers. Frost patterns adorn the glass, adding depth and realism to the scene. Above the dancer, image wide bold red text reads "WAN 2.2"; smaller black text in a cyan circle "14B" appears in the upper-left corner, subtly indicating version information. The overall mood is serene yet dynamic, blending elegance with urban coldness, illuminated by warm contrasts between the dancer’s motion and the stark beauty of the nighttime landscape. Parameters: Steps: 20| Size: 512x512| Seed: 324| CFG scale: 6| App: SD.Next| Version: 6ea881b| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-T2V-A14B-Diffusers |
https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B
https://github.com/Wan-Video/Wan2.2
...
Test 0 - Different seed variations
Low Noise only
| CFG6, STEP 20 | Seed: 1620085323 | Seed:1931701040 | Seed:4075624134 | Seed:2736029172 |
|---|---|---|---|---|
hand and face and bookshop girl |
|
|
|
|
Combined (Low and high Noise)
...
Time: 28m 2.91s | total 1729.31 pipeline 1682.88 preview 43.76 te 2.32 vae 0.32 | GPU 70822 MB 55% | RAM 97.11 GB 77%
...
77%
| 8 | 16 | 20 | 32 | |
|---|---|---|---|---|
CFG1 |
|  |  |
|
CFG2 |
|
|
|
|
CFG3 |
|
|
|
|
CFG4 |
|
|
|
|
CFG5 |
|
|
|
|
CFG6 |
|
|
|
|
CFG8 |
|
|
|
|
...
CFG1
...
CFG2
...
CFG3
...
CFG4
...
CFG5
...
CFG6
...
...
CFG8
Other model covers
System info
| Code Block |
|---|
Fri Oct 24 15:48:18 2025 app: sdnext.git updated: 2025-10-23 hash: c9fdd56eb url: https://github.com/liutyi/sdnext.git/tree/pytorch arch: x86_64 cpu: x86_64 system: Linux release: 6.14.0-33-generic python: 3.12.3 pytorch 2.9.0+xpu device: Intel(R) Arc(TM) Graphics (1) ipex: ram: free:121.55 used:3.78 total:125.33 xformers: diffusers: 0.36.0.dev0 transformers: 4.57.1 active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 base: Diffusers/Wan-AI/Wan2.2-T2V-A14B-Diffusers [5be7df9619] refiner: none vae: none te: none unet: none ipex native Scaled-Dot-Product |
...
| Code Block |
|---|
{
"sd_model_checkpoint": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
"diffusers_to_gpu": true,
"device_map": "gpu",
"diffusers_offload_mode": "none",
"sdnq_dequantize_compile": false,
"ui_request_timeout": 300000,
"huggingface_token": "hf..FraU",
"diffusers_version": "b3e9dfced7c9e8d00f646c710766b532383f04c6",
"sd_checkpoint_hash": "6681e8e4b134c81f16533acedb0d406d7e5e366e1624b4105178c64d00b05d51",
"civitai_token": "f1..65",
"model_wan_stage": "combined"
} |
Model info
| Module | Class | Device | Dtype | Quant | Params | Modules | Config |
|---|---|---|---|---|---|---|---|
| vae | AutoencoderKLWan | cpu | torch.bfloat16 | None | 126892531 | 260 | FrozenDict({'base_dim': 96, 'decoder_base_dim': None, 'z_dim': 16, 'dim_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_scales': [], 'temperal_downsample': [False, True, True], 'dropout': 0.0, 'latents_mean': [-0.7571, -0.7089, -0.9113, 0.1075, -0.1745, 0.9653, -0.1517, 1.5508, 0.4134, -0.0715, 0.5517, -0.3632, -0.1922, -0.9497, 0.2503, -0.2921], 'latents_std': [2.8184, 1.4541, 2.3275, 2.6558, 1.2196, 1.7708, 2.6052, 2.0743, 3.2687, 2.1526, 2.8652, 1.5579, 1.6382, 1.1253, 2.8251, 1.916], 'is_residual': False, 'in_channels': 3, 'out_channels': 3, 'patch_size': None, 'scale_factor_temporal': 4, 'scale_factor_spatial': 8, '_use_default_values': ['scale_factor_spatial', 'is_residual', 'scale_factor_temporal', 'in_channels', 'patch_size', 'out_channels', 'decoder_base_dim'], '_class_name': 'AutoencoderKLWan', '_diffusers_version': '0.35.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--Wan-AI--Wan2.2-T2V-A14B-Diffusers/snapshots/5be7df9619b54f4e2667b2755bc6a756675b5cd7/vae'}) |
| text_encoder | UMT5EncoderModel | xpu:0 | torch.bfloat16 | None | 5680910336 | 486 | UMT5Config { "architectures": [ "UMT5EncoderModel" ], "classifier_dropout": 0.0, "d_ff": 10240, "d_kv": 64, "d_model": 4096, "decoder_start_token_id": 0, "dense_act_fn": "gelu_new", "dropout_rate": 0.1, "dtype": "bfloat16", "eos_token_id": 1, "feed_forward_proj": "gated-gelu", "initializer_factor": 1.0, "is_encoder_decoder": true, "is_gated_act": true, "layer_norm_epsilon": 1e-06, "model_type": "umt5", "num_decoder_layers": 24, "num_heads": 64, "num_layers": 24, "output_past": true, "pad_token_id": 0, "relative_attention_max_distance": 128, "relative_attention_num_buckets": 32, "scalable_attention": true, "tie_word_embeddings": false, "tokenizer_class": "T5Tokenizer", "transformers_version": "4.57.1", "use_cache": true, "vocab_size": 256384 } |
| tokenizer | T5TokenizerFast | None | None | None | 0 | 0 | None |
| transformer | WanTransformer3DModel | xpu:0 | torch.bfloat16 | None | 14288491584 | 1138 | FrozenDict({'patch_size': [1, 2, 2], 'num_attention_heads': 40, 'attention_head_dim': 128, 'in_channels': 16, 'out_channels': 16, 'text_dim': 4096, 'freq_dim': 256, 'ffn_dim': 13824, 'num_layers': 40, 'cross_attn_norm': True, 'qk_norm': 'rms_norm_across_heads', 'eps': 1e-06, 'image_dim': None, 'added_kv_proj_dim': None, 'rope_max_seq_len': 1024, 'pos_embed_seq_len': None, '_class_name': 'WanTransformer3DModel', '_diffusers_version': '0.35.0.dev0', '_name_or_path': 'Wan-AI/Wan2.2-T2V-A14B-Diffusers'}) |
| scheduler | UniPCMultistepScheduler | None | None | None | 0 | 0 | FrozenDict({'num_train_timesteps': 1000, 'beta_start': 0.0001, 'beta_end': 0.02, 'beta_schedule': 'linear', 'trained_betas': None, 'solver_order': 2, 'prediction_type': 'flow_prediction', 'thresholding': False, 'dynamic_thresholding_ratio': 0.995, 'sample_max_value': 1.0, 'predict_x0': True, 'solver_type': 'bh2', 'lower_order_final': True, 'disable_corrector': [], 'solver_p': None, 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False, 'use_flow_sigmas': True, 'flow_shift': 3.0, 'timestep_spacing': 'linspace', 'steps_offset': 0, 'final_sigmas_type': 'zero', 'rescale_betas_zero_snr': False, 'use_dynamic_shifting': False, 'time_shift_type': 'exponential', '_class_name': 'UniPCMultistepScheduler', '_diffusers_version': '0.35.0.dev0'}) |
| transformer_2 | WanTransformer3DModel | xpu:0 | torch.bfloat16 | None | 14288491584 | 1138 | FrozenDict({'patch_size': [1, 2, 2], 'num_attention_heads': 40, 'attention_head_dim': 128, 'in_channels': 16, 'out_channels': 16, 'text_dim': 4096, 'freq_dim': 256, 'ffn_dim': 13824, 'num_layers': 40, 'cross_attn_norm': True, 'qk_norm': 'rms_norm_across_heads', 'eps': 1e-06, 'image_dim': None, 'added_kv_proj_dim': None, 'rope_max_seq_len': 1024, 'pos_embed_seq_len': None, '_class_name': 'WanTransformer3DModel', '_diffusers_version': '0.35.0.dev0', '_name_or_path': 'Wan-AI/Wan2.2-T2V-A14B-Diffusers'}) |
| boundary_ratio | float | None | None | None | 0 | 0 | None |
| expand_timesteps | bool | None | None | None | 0 | 0 | None |