Info
Negative prompt have significant impact on image quality
https://huggingface.co/Wan-AI/Wan2.2-TI2V-5B-Diffusers
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: 20| Size: 1024x1024| Seed: 2736029172| CFG scale: 5| App: SD.Next| Version: 7644432| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-TI2V-5B-Diffusers
Time: 1m 11.48s | total 73.03 pipeline 71.44 te 1.34 | GPU 29768 MB 24% | RAM 38.63 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
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: 1024x1024| Seed: 2736029172| CFG scale: 5| App: SD.Next| Version: 7644432| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-TI2V-5B-Diffusers
285H Time: 2m 52.36s | total 174.08 pipeline 172.32 te 1.38 | GPU 29768 MB 24% | RAM 38.68 GB 31%
| 8 | 16 | 20 | 32 | 50 | |
|---|---|---|---|---|---|
CFG1 |
|
|
|
|
|
CFG2 |
|
|
|
|
|
CFG3 |
|
|
|
|
|
CFG4 |
|
|
|
|
|
CFG5 |
|
|
|
|
|
CFG6 |
|
|
|
|
|
CFG10 |
|
|
|
|
|
Test 2 - Face and hand
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: 32| Size: 1024x1024| Seed: 1931701040| CFG scale: 4| App: SD.Next| Version: 7644432| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-TI2V-5B-Diffusers
Time: 1m 51.74s | total 113.37 pipeline 111.71 te 1.37 | GPU 29768 MB 24% | RAM 38.83 GB 32%
| 16 | 20 | 32 | 64 | |
|---|---|---|---|---|
CFG2 |
|
|
|
|
CFG4 |
|
|
|
|
CFG6 |
|
|
|
|
CFG8 |
|
|
|
|
CFG10 |
|
|
|
|
Test 3 - Legs
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.
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: 32| Size: 1024x1024| Seed: 4075624134| CFG scale: 4| App: SD.Next| Version: 7644432| Pipeline: WanPipeline| Operations: txt2img| Model: Wan2.2-TI2V-5B-Diffusers
285H Time: 1m 51.81s | total 113.45 pipeline 111.76 te 1.38 | GPU 29768 MB 24% | RAM 38.76 GB 31%
| 16 | 24 | 32 | 50 | |
|---|---|---|---|---|
CFG3 |
|
|
|
|
CFG3.5 |
|
|
|
|
CFG4 |
|
|
|
|
CFG4.5 |
|
|
|
|
CFG5 |
|
|
|
|
Test 4 - Other covers
1024px, CFG5, 20 steps, with standard negative prompt
Test 5 - some art prompts
System info
app: sdnext.git updated: 2025-12-06 hash: 764443213 url: https://github.com/liutyi/sdnext/tree/pytorch arch: x86_64 cpu: x86_64 system: Linux release: 6.17.0-7-generic python: 3.12.3 Torch 2.9.1+xpu ram: free:114.91 used:8.17 total:123.07 device: Intel(R) Arc(TM) Graphics (1) ipex: 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-TI2V-5B-Diffusers [b8fff7315c] refiner: none vae: none te: none unet: none
Config
{
"diffusers_version": "a1f36ee3ef4ae1bf98bd260e539197259aa981c1",
"sd_model_checkpoint": "Diffusers/Wan-AI/Wan2.2-TI2V-5B-Diffusers [b8fff7315c]",
"diffusers_offload_mode": "none",
"ui_request_timeout": 300000,
"huggingface_token": "hf_..FraU",
"sd_checkpoint_hash": null,
"model_wan_stage": "combined"
}
Model info
Diffusers/Wan-AI/Wan2.2-TI2V-5B-Diffusers [b8fff7315c]
| Module | Class | Device | Dtype | Quant | Params | Modules | Config |
|---|---|---|---|---|---|---|---|
| vae | AutoencoderKLWan | xpu:0 | torch.bfloat16 | None | 704688668 | 272 | FrozenDict({'base_dim': 160, 'decoder_base_dim': 256, 'z_dim': 48, 'dim_mult': [1, 2, 4, 4], 'num_res_blocks': 2, 'attn_scales': [], 'temperal_downsample': [False, True, True], 'dropout': 0.0, 'latents_mean': [-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': [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': '0.35.0.dev0', 'clip_output': False, '_name_or_path': '/mnt/models/Diffusers/models--Wan-AI--Wan2.2-TI2V-5B-Diffusers/snapshots/b8fff7315c768468a5333511427288870b2e9635/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 | 4999787712 | 858 | FrozenDict({'patch_size': [1, 2, 2], 'num_attention_heads': 24, 'attention_head_dim': 128, 'in_channels': 48, 'out_channels': 48, 'text_dim': 4096, 'freq_dim': 256, 'ffn_dim': 14336, '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, '_class_name': 'WanTransformer3DModel', '_diffusers_version': '0.35.0.dev0', '_name_or_path': 'Wan-AI/Wan2.2-TI2V-5B-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': 5.0, '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 | NoneType | None | None | None | 0 | 0 | None |
| boundary_ratio | NoneType | None | None | None | 0 | 0 | None |
| expand_timesteps | bool | None | None | None | 0 | 0 | None |
