Info
https://huggingface.co/Wan-AI/Wan2.12-TI2V-T2V5B-14BDiffusers
Note:
If you are using theT2V-1.3Bmodel, we recommend setting the parameter--sample_guide_scale 6.
The--sample_shift parametercan be adjusted within the range of 8 to 12 based on the performance.
| Code Block |
|---|
model_id = "Wan-AI/Wan2.2-TI2V-5B-Diffusers"
height = 704
width = 1280
num_frames = 121
num_inference_steps = 50
guidance_scale = 5.0
prompt = "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."
negative_prompt = "色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
#negative_prompt = "Vibrant colors, overexposed, static, blurry details, subtitles, style, artwork, painting, image, still, overall grayish, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, distorted limbs, fingers fused together, static image, cluttered background, three legs, many people in the background, walking backwards." |
Test 0 - Different seed variations and resolutions
Prompt: Create a close-up photograph of a woman's face and hand, 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 face.
Negative: Vibrant colors, overexposed, static, blurry details, subtitles, style, artwork, painting, image, still, overall grayish, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, distorted limbs, fingers fused together, static image, cluttered background, three legs, many people in the background, walking backwards.
Parameters: Steps: 50| Size: 704x704| Seed: 2736029172| CFG scale: 5| App: SD.Next| Version: 7644432| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-TI2V-5B-Diffusers
Time: 1m 36.82s | total 99.75 pipeline 96.79 te 1.37 vae 1.36 | GPU 29768 MB 24% | RAM 38.62 GB 31%
| CFG5, STEP20 | Seed: 1620085323 | Seed:1931701040 | Seed:4075624134 | Seed:2736029172 |
|---|---|---|---|---|
| bookshop girl | ||||
| hand and face | ||||
| legs and shoes |
Test 1 - Bookshop
Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
...
Execution: Time: 3m 54.34s | total 439.88 pipeline 233.25 preview 194.33 te 5.20 offload 5.07 vae 1.20 decode 0.80 post 0.27 gc
| 8 | 16 | 20 | 32 | |
|---|---|---|---|---|
CFG4 | ||||
CFG6 | ||||
CFG8 | ||||
CFG10 |
Test 4 - Different seed variations and resolutions
Prompt: Create a close-up photograph of a woman's face and hand, 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 face.
Parameters: Steps: 20| Size: 768x768| Seed: 2736029172| CFG scale: 6| App: SD.Next| Version: 7644432| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-TI2V-5B-Diffusers
Time: 45.33s | total 48.41 pipeline 45.30 vae 1.66 te 1.36 | GPU 24466 MB 19% | RAM 34.07 GB 28%
| CFG6, STEP 20 | Seed: 1620085323 | Seed:1931701040 | Seed:4075624134 | Seed:2736029172 | |||
|---|---|---|---|---|---|---|---|
512px combined |
|
|
|
| |||
| 768px |
|
|
|
| |||
| 1024px |
|
| 1280px
System info
| Code Block |
|---|
app: sdnext.git updated: 2025-0712-2106 hash: 34031f54764443213 url: https://github.com/vladmandicliutyi/sdnext.git/tree/devpytorch arch: x86_64 cpu: x86_64 system: Linux release: 6.1417.0-247-generic python: 3.12.3 Torch 2.79.1+xpu ram: free:114.91 used:8.17 total:123.07 device: Intel(R) Arc(TM) Graphics (1) ipex: xformers: diffusers: 0.3536.0.dev0 transformers: 4.5357.21 active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 base: Diffusers/Wan-AI/Wan2.12-T2VTI2V-1.3B5B-Diffusers [0fad780a53b8fff7315c] refiner: none vae: none te: none unet: none |
Config
| Code Block |
|---|
{
"sd_model_checkpoint": "Diffusers/Wan-AI/Wan2.1-T2V-1.3B-Diffusers [0fad780a53]",
"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
| Module | Class | Device | Dtype | DTypeQuant | Params | Modules | Config | ||
|---|---|---|---|---|---|---|---|---|---|
| vae | AutoencoderKLWan | xpu:0 | torch.bfloat16 | None126892531 | 704688668 | 260272 | FrozenDict({'base_dim': 160, 'decoder_base_dim': 96256, 'z_dim': 1648, '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, -0.2921-0.2289, -0.0052, -0.1323, -0.2339, -0.2799, 0.0174, 0.1838, 0.1557, -0.1382, 0.0542, 0.2813, 0.0891, 0.157, -0.0098, 0.0375, -0.1825, -0.2246, -0.1207, -0.0698, 0.5109, 0.2665, -0.2108, -0.2158, 0.2502, -0.2055, -0.0322, 0.1109, 0.1567, -0.0729, 0.0899, -0.2799, -0.123, -0.0313, -0.1649, 0.0117, 0.0723, -0.2839, -0.2083, -0.052, 0.3748, 0.0152, 0.1957, 0.1433, -0.2944, 0.3573, -0.0548, -0.1681, -0.0667], '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]0.4765, 1.0364, 0.4514, 1.1677, 0.5313, 0.499, 0.4818, 0.5013, 0.8158, 1.0344, 0.5894, 1.0901, 0.6885, 0.6165, 0.8454, 0.4978, 0.5759, 0.3523, 0.7135, 0.6804, 0.5833, 1.4146, 0.8986, 0.5659, 0.7069, 0.5338, 0.4889, 0.4917, 0.4069, 0.4999, 0.6866, 0.4093, 0.5709, 0.6065, 0.6415, 0.4944, 0.5726, 1.2042, 0.5458, 1.6887, 0.3971, 1.06, 0.3943, 0.5537, 0.5444, 0.4089, 0.7468, 0.7744], 'is_residual': True, 'in_channels': 12, 'out_channels': 12, 'patch_size': 2, 'scale_factor_temporal': 4, 'scale_factor_spatial': 16, '_class_name': 'AutoencoderKLWan', '_diffusers_version': '0.3335.0.dev0', 'clip_output': False, '_name_or_path': '/mnt/models/Diffusers/models--Wan-AI--Wan2.12-T2VTI2V-1.3B5B-Diffusers/snapshots/0fad780a534b6463e45facd96134c9f345acfa5bb8fff7315c768468a5333511427288870b2e9635/vae'}) | ||
| text_encoder | UMT5EncoderModelcpu | xpu:0 | torch.bfloat165680910336 | 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", "torch_dtype": "bfloat16", "transformers_version": "4.5357.21", "use_cache": true, "vocab_size": 256384 } | ||
| tokenizer | T5TokenizerFast | None | None | None | 0 | 0 | None | ||
| transformer | WanTransformer3DModel | xpu:0 | torch.bfloat16 | None | 49997877121418996800 | 858 | FrozenDict({'patch_size': [1, 2, 2], 'num_attention_heads': 1224, 'attention_head_dim': 128, 'in_channels': 1648, 'out_channels': 1648, 'text_dim': 4096, 'freq_dim': 256, 'ffn_dim': 896014336, 'num_layers': 30, '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, '_use_default_values ': ['pos_embed_seq_len'], '_class_name': 'WanTransformer3DModel', '_diffusers_version': '0.3335.0.dev0', '_name_or_path': 'Wan-AI/Wan2.12-T2VTI2V-1.3B5B-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': 35.0, 'timestep_spacing': 'linspace', 'steps_offset': 0, 'final_sigmas_type': 'zero', 'rescale_betas_zero_snr': False, 'use_dynamic_shifting': False, 'time_shift_type': 'exponential', '_use_default_values': ['use_dynamic_shifting', 'time_shift_type'], '_class_name': 'UniPCMultistepScheduler', '_diffusers_version': '0.3335.0.dev0'}) | ||
| transformer_2 | NoneType | None | _name_or_path | str | None | None | 0 | 0 | None |
| boundary_ratio | NoneType | None | _class_name | str | None | None | 0 | 0 | None |
| expand_timesteps | bool | None | _diffusers_version | str | None | None | 0 | 0 | None |