https://huggingface.co/circlestone-labs/Anima
https://huggingface.co/CalamitousFelicitousness/Anima-sdnext-diffusers

Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
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.
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.
| CFG4.5, STEP50 | Seed: 1620085323 | Seed:1931701040 | Seed:4075624134 | Seed:2736029172 |
|---|---|---|---|---|
| Bookshop girl |
|
|
|
|
| Face and hand |
|
|
|
|
| Legs and shoes |
|
|
|
|
Prompt: photorealistic girl in bookshop choosing the book in romantic stories shelf. smiling
Parameters: Steps: 30| Size: 1024x1024| Seed: 1620085323| CFG scale: 4| App: SD.Next| Version: c7ecba6| Pipeline: AnimaTextToImagePipeline| Operations: txt2img| Model: Anima-sdnext-diffusers
285H Time: 2m 26.69s | total 151.26 pipeline 146.65 preview 3.29 callback 0.98 | GPU 10654 MB 8% | RAM 22.38 GB 18%
| 5 | 10 | 20 | 30 | 40 | 50 | 100 | |
|---|---|---|---|---|---|---|---|
| CFG1 |
|
|
|
|
|
|
|
| CFG2 |
|
|
|
|
|
|
|
| CFG3 |
|
|
|
|
|
|
|
| CFG4 |
|
|
|
|
|
|
|
| CFG5 |
|
|
|
|
|
|
|
| CFG6 |
|
|
|
|
|
|
|
| CFG8 |
|
|
|
|
|
|
|
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: 32| Size: 1024x1024| Seed: 4075624134| CFG scale: 4| App: SD.Next| Version: c7ecba6| Pipeline: AnimaTextToImagePipeline| Operations: txt2img| Model: Anima-sdnext-diffusers
285H Time: 2m 40.12s | total 170.54 pipeline 160.07 preview 9.08 callback 1.06 | GPU 10654 MB 8% | RAM 22.48 GB 18%
| 8 | 16 | 32 | 64 | |
|---|---|---|---|---|
| CFG4 |
|
|
|
|
| CFG4.5 |
|
|
|
|
| CFG4.75 |
|
|
|
|
| CFG5 |
|
|
|
|
| CFG6 |
|
|
|
|
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.
| 8 | 16 | 32 | 64 | |
|---|---|---|---|---|
| CFG3 |
|
|
|
|
| CFG4 |
|
|
|
|
| CFG4.5 |
|
|
|
|
| CFG5 |
|
|
|
|
| CFG5.5 |
|
|
|
|
| CFG6 |
|
|
|
|
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
![]()
| seed:1 | seed:2 | seed:3 | seed:4 | seed:5 |
|---|---|---|---|---|
|
|
|
|
|
| seed:6 | seed:7 | seed:8 | seed:9 | seed:10 |
|
|
|
|
|
| seed:21 | seed:42 | seed:68 | seed:324 | seed:2026 |
|
|
|
|
|
| Cosmos 2B - 170 seconds | Anima 2B - 170 seconds | WAI Illustrious XL v15 2.5B - 50 seconds | Z Image Turbo (7B) - 60 seconds |
|---|---|---|---|
Prompt: masterpiece, best quality, score_7, safe. An anime girl wearing a black tank-top and denim shorts is standing outdoors. She's holding a rectangular sign out in front of her that reads "COSMOS" in solid white text. She's looking at the viewer with a smile. The background features some trees and blue sky with clouds. In the top left corner there is "2B" written in white drippy text. Negative: out of frame, cropped Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: Cosmos2TextToImagePipeline| Operations: txt2img| Model: Cosmos-Predict2-2B-Text2Image Time: 2m 52.28s | total 452.06 pipeline 172.23 preview 139.04 callback 137.51 te 2.23 vae 1.01 | GPU 18668 MB 15% | RAM 36.1 GB 29% |
Prompt: masterpiece, best quality, score_7, safe. An anime girl wearing a black tank-top and denim shorts is standing outdoors. She's holding a rectangular sign out in front of her that reads "ANIMA" in solid white text. She's looking at the viewer with a smile. The background features some trees and blue sky with clouds. In the top left corner there is "2B" written in white drippy text. Negative: out of frame, cropped Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: AnimaTextToImagePipeline| Operations: txt2img| Model: Anima-sdnext-diffusers Time: 2m 50.03s | total 442.83 pipeline 169.98 callback 137.80 preview 134.76 | GPU 10784 MB 9% | RAM 25.57 GB 21% |
Prompt: masterpiece, best quality, score_7, safe. An anime girl wearing a black tank-top and denim shorts is standing outdoors. She's holding a rectangular sign out in front of her that reads "WAI" in solid white text. She's looking at the viewer with a smile. The background features some trees and blue sky with clouds. In the top left corner there is "2B" written in white drippy text. Negative: out of frame, cropped Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 7| App: SD.Next| Version: 5b0f86b| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: waiIllustriousSDXL_v150| Model hash: befc694a29 Time: 50.52s | total 120.96 pipeline 48.56 callback 41.03 preview 28.63 decode 1.89 gc 0.44 prompt 0.34 | GPU 10602 MB 8% | RAM 18.77 GB 15% |
Prompt: masterpiece, best quality, score_7, safe. An anime girl wearing a black tank-top and denim shorts is standing outdoors. She's holding a rectangular sign out in front of her that reads "Z IMAGE ⚡" in solid white text. She's looking at the viewer with a smile. The background features some trees and blue sky with clouds. In the top left corner there is "7B" written in white drippy text. Negative: out of frame, cropped Parameters: Steps: 9| Size: 1024x1024| Seed: 42| CFG scale: 1.0| App: SD.Next| Version: 5b0f86b| Pipeline: ZImagePipeline| Operations: txt2img| Model: Z-Image-Turbo Time: 1m 4.03s | total 167.43 pipeline 61.32 preview 53.37 callback 49.07 decode 2.66 te 0.52 gc 0.45 | GPU 23660 MB 19% | RAM 51.54 GB 42% |
Prompt: mature female, solo, breasts, red hair, long hair, red eyes, large breasts, sunglasses, looking over eyewear, hair over one eye, sweater, looking at viewer, sleeveless, watch, adjusting eyewear, kirijou mitsuru, white sweater, bare shoulders, turtleneck, wristwatch, bangs, smile, tinted eyewear ,abstract background, foreshortening, masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: Cosmos2TextToImagePipeline| Operations: txt2img| Model: Cosmos-Predict2-2B-Text2Image 285H Time: 2m 50.14s | total 442.44 pipeline 170.10 callback 146.17 preview 123.99 te 2.11 | GPU 18516 MB 15% | RAM 25.93 GB 21% |
Prompt: mature female, solo, breasts, red hair, long hair, red eyes, large breasts, sunglasses, looking over eyewear, hair over one eye, sweater, looking at viewer, sleeveless, watch, adjusting eyewear, kirijou mitsuru, white sweater, bare shoulders, turtleneck, wristwatch, bangs, smile, tinted eyewear ,abstract background, foreshortening, masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: AnimaTextToImagePipeline| Operations: txt2img| Model: Anima-sdnext-diffusers Time: 2m 50.06s | total 455.26 pipeline 170.02 preview 143.23 callback 141.74 | GPU 10784 MB 9% | RAM 25.56 GB 21% |
Prompt: mature female, solo, breasts, red hair, long hair, red eyes, large breasts, sunglasses, looking over eyewear, hair over one eye, sweater, looking at viewer, sleeveless, watch, adjusting eyewear, kirijou mitsuru, white sweater, bare shoulders, turtleneck, wristwatch, bangs, smile, tinted eyewear ,abstract background, foreshortening, masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 7| App: SD.Next| Version: 5b0f86b| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: waiIllustriousSDXL_v150| Model hash: befc694a29 Time: 50.08s | total 118.48 pipeline 48.16 callback 39.72 preview 28.26 decode 1.88 gc 0.43 | GPU 10602 MB 8% | RAM 18.78 GB 15% |
Prompt: mature female, solo, breasts, red hair, long hair, red eyes, large breasts, sunglasses, looking over eyewear, hair over one eye, sweater, looking at viewer, sleeveless, watch, adjusting eyewear, kirijou mitsuru, white sweater, bare shoulders, turtleneck, wristwatch, bangs, smile, tinted eyewear ,abstract background, foreshortening, masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 9| Size: 1024x1024| Seed: 42| CFG scale: 1.0| App: SD.Next| Version: 5b0f86b| Pipeline: ZImagePipeline| Operations: txt2img| Model: Z-Image-Turbo Time: 59.92s | total 108.08 pipeline 57.55 callback 37.01 preview 10.22 decode 2.32 te 0.48 gc 0.43 | GPU 23636 MB 19% | RAM 45.18 GB 37% |
Prompt: 1girl, hatsune miku, dress, long hair, jewelry, white dress, blue eyes, necklace, bubble, solo, underwater, hair between eyes, looking at viewer, bangs, blue hair, bow, reaching towards viewer, blue theme, air bubble, hair bow, collarbone, floating hair, frills, twintails, blurry foreground, frilled dress, off-shoulder dress, bare shoulders, blurry, very long hair ,masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: Cosmos2TextToImagePipeline| Operations: txt2img| Model: Cosmos-Predict2-2B-Text2Image 285H Time: 2m 51.57s | total 462.25 pipeline 171.52 preview 145.39 callback 143.14 te 2.10 | GPU 18516 MB 15% | RAM 25.92 GB 21% |
Prompt: 1girl, hatsune miku, dress, long hair, jewelry, white dress, blue eyes, necklace, bubble, solo, underwater, hair between eyes, looking at viewer, bangs, blue hair, bow, reaching towards viewer, blue theme, air bubble, hair bow, collarbone, floating hair, frills, twintails, blurry foreground, frilled dress, off-shoulder dress, bare shoulders, blurry, very long hair ,masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: AnimaTextToImagePipeline| Operations: txt2img| Model: Anima-sdnext-diffusers Time: 2m 49.74s | total 434.46 pipeline 169.65 preview 132.45 callback 128.52 te 2.78 vae 0.97 | GPU 10784 MB 9% | RAM 25.53 GB 21% |
Prompt: 1girl, hatsune miku, dress, long hair, jewelry, white dress, blue eyes, necklace, bubble, solo, underwater, hair between eyes, looking at viewer, bangs, blue hair, bow, reaching towards viewer, blue theme, air bubble, hair bow, collarbone, floating hair, frills, twintails, blurry foreground, frilled dress, off-shoulder dress, bare shoulders, blurry, very long hair ,masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 7| App: SD.Next| Version: 5b0f86b| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: waiIllustriousSDXL_v150| Model hash: befc694a29 Time: 50.14s | total 117.81 pipeline 48.19 callback 38.90 preview 28.34 decode 1.89 gc 0.43 | GPU 10602 MB 8% | RAM 18.81 GB 15% |
Prompt: 1girl, hatsune miku, dress, long hair, jewelry, white dress, blue eyes, necklace, bubble, solo, underwater, hair between eyes, looking at viewer, bangs, blue hair, bow, reaching towards viewer, blue theme, air bubble, hair bow, collarbone, floating hair, frills, twintails, blurry foreground, frilled dress, off-shoulder dress, bare shoulders, blurry, very long hair ,masterpiece,best quality,amazing quality Negative: bad quality,worst quality,worst detail,sketch,censor Parameters: Steps: 9| Size: 1024x1024| Seed: 42| CFG scale: 1.0| App: SD.Next| Version: 5b0f86b| Pipeline: ZImagePipeline| Operations: txt2img| Model: Z-Image-Turbo Time: 59.81s | total 108.40 pipeline 57.43 callback 41.00 preview 6.68 decode 2.33 te 0.48 gc 0.43 | GPU 23636 MB 19% | RAM 45.21 GB 37% |
Prompt: Naruto vs Sasuke final battle Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: Cosmos2TextToImagePipeline| Operations: txt2img| Model: Cosmos-Predict2-2B-Text2Image 285H Time: 2m 51.47s | total 449.57 pipeline 171.42 preview 141.22 callback 134.72 te 2.12 | GPU 18516 MB 15% | RAM 25.94 GB 21% |
Prompt: Naruto vs Sasuke final battle Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: AnimaTextToImagePipeline| Operations: txt2img| Model: Anima-sdnext-diffusers Time: 2m 50.34s | total 462.06 pipeline 170.29 callback 147.75 preview 143.46 te 0.46 | GPU 10784 MB 9% | RAM 25.55 GB 21% |
Prompt: Naruto vs Sasuke final battle Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 7| App: SD.Next| Version: 5b0f86b| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: waiIllustriousSDXL_v150| Model hash: befc694a29 Time: 53.09s | total 131.10 pipeline 50.15 callback 42.47 preview 34.85 decode 2.89 gc 0.48 | GPU 10606 MB 8% | RAM 38.66 GB 31% |
Prompt: Naruto vs Sasuke final battle Parameters: Steps: 9| Size: 1024x1024| Seed: 42| CFG scale: 1.0| App: SD.Next| Version: 5b0f86b| Pipeline: ZImagePipeline| Operations: txt2img| Model: Z-Image-Turbo Time: 1m 0.65s | total 108.69 pipeline 58.28 callback 41.51 preview 5.60 decode 2.33 te 0.49 gc 0.44 | GPU 23636 MB 19% | RAM 44.34 GB 36% |
Prompt: looking at viewer, sitting, chair, 1girl, solo, the herta, purple eyes, witch hat, long hair, gradient hair, pantyhose, uneven footwear, boots,, masterpiece,best quality Negative: bad quality,worst quality,worst detail Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: Cosmos2TextToImagePipeline| Operations: txt2img| Model: Cosmos-Predict2-2B-Text2Image 285H Time: 2m 51.52s | total 466.14 pipeline 171.48 callback 147.49 preview 144.96 te 2.13 | GPU 18516 MB 15% | RAM 25.94 GB 21% |
Prompt: looking at viewer, sitting, chair, 1girl, solo, the herta, purple eyes, witch hat, long hair, gradient hair, pantyhose, uneven footwear, boots,, masterpiece,best quality Negative: bad quality,worst quality,worst detail Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 4| App: SD.Next| Version: 5b0f86b| Pipeline: AnimaTextToImagePipeline| Operations: txt2img| Model: Anima-sdnext-diffusers Time: 2m 50.08s | total 455.30 pipeline 170.04 preview 142.77 callback 142.24 | GPU 10784 MB 9% | RAM 25.56 GB 21% |
Prompt: looking at viewer, sitting, chair, 1girl, solo, the herta, purple eyes, witch hat, long hair, gradient hair, pantyhose, uneven footwear, boots,, masterpiece,best quality Negative: bad quality,worst quality,worst detail Parameters: Steps: 35| Size: 1024x1024| Seed: 42| CFG scale: 7| App: SD.Next| Version: 5b0f86b| Pipeline: StableDiffusionXLPipeline| Operations: txt2img| Model: waiIllustriousSDXL_v150| Model hash: befc694a29 Time: 49.96s | total 119.30 pipeline 48.01 callback 40.54 preview 28.14 decode 1.89 gc 0.44 | GPU 10600 MB 8% | RAM 18.83 GB 15% |
Prompt: looking at viewer, sitting, chair, 1girl, solo, the herta, purple eyes, witch hat, long hair, gradient hair, pantyhose, uneven footwear, boots,, masterpiece,best quality Negative: bad quality,worst quality,worst detail Parameters: Steps: 9| Size: 1024x1024| Seed: 42| CFG scale: 1.0| App: SD.Next| Version: 5b0f86b| Pipeline: ZImagePipeline| Operations: txt2img| Model: Z-Image-Turbo Time: 59.54s | total 107.56 pipeline 57.16 callback 42.06 preview 5.00 decode 2.33 te 0.52 gc 0.44 | GPU 23636 MB 19% | RAM 45.24 GB 37% |
Tue Feb 3 12:50:13 2026 app: sdnext.git updated: 2026-02-02 hash: c7ecba67c tag: tags: url: https://github.com/liutyi/sdnext/tree/pytorch arch: x86_64 cpu: x86_64 system: Linux release: 6.17.0-8-generic python: 3.12.3 Pytorch: 2.10.0+xpu device: Intel(R) Arc(TM) Graphics (1) ipex: ram: free:112.69 used:10.38 total:123.07 xformers: diffusers: 0.37.0.dev0 transformers: 4.57.5 active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16 base: CalamitousFelicitousness/Anima-sdnext-diffusers refiner: none vae: none te: none unet: none Backend: ipex Pipeline: native Memory optimization: none Cross-attention: Scaled-Dot-Product |
. |
CalamitousFelicitousness/Anima-sdnext-diffusers
| Module | Class | Device | Dtype | Quant | Params | Modules | Config |
|---|---|---|---|---|---|---|---|
| text_encoder | Qwen3Model | xpu:0 | torch.bfloat16 | None | 596049920 | 425 | Qwen3Config { "architectures": [ "Qwen3Model" ], "attention_bias": false, "attention_dropout": 0.0, "dtype": "bfloat16", "head_dim": 128, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3072, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "4.57.5", "use_cache": false, "use_sliding_window": false, "vocab_size": 151936 } |
| tokenizer | Qwen2TokenizerFast | None | None | None | 0 | 0 | None |
| t5_tokenizer | T5TokenizerFast | None | None | None | 0 | 0 | None |
| llm_adapter | AnimaLLMAdapter | xpu:0 | torch.bfloat16 | None | 134663680 | 139 | FrozenDict({'source_dim': 1024, 'target_dim': 1024, 'model_dim': 1024, 'num_layers': 6, 'num_heads': 16, 'mlp_ratio': 4.0, 'vocab_size': 32128, 'use_self_attn': True, '_class_name': 'AnimaLLMAdapter', '_diffusers_version': '0.37.0', '_name_or_path': 'CalamitousFelicitousness/Anima-sdnext-diffusers'}) |
| transformer | CosmosTransformer3DModel | xpu:0 | torch.bfloat16 | None | 1956405248 | 1138 | FrozenDict({'in_channels': 16, 'out_channels': 16, 'num_attention_heads': 16, 'attention_head_dim': 128, 'num_layers': 28, 'mlp_ratio': 4.0, 'text_embed_dim': 1024, 'adaln_lora_dim': 256, 'max_size': [128, 240, 240], 'patch_size': [1, 2, 2], 'rope_scale': [1.0, 4.0, 4.0], 'concat_padding_mask': True, 'extra_pos_embed_type': None, 'use_crossattn_projection': False, 'crossattn_proj_in_channels': 1024, 'encoder_hidden_states_channels': 1024, '_use_default_values': ['use_crossattn_projection', 'crossattn_proj_in_channels', 'encoder_hidden_states_channels'], '_class_name': 'CosmosTransformer3DModel', '_diffusers_version': '0.37.0', '_name_or_path': 'CalamitousFelicitousness/Anima-sdnext-diffusers'}) |
| vae | AutoencoderKLWan | xpu:0 | 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': ['is_residual', 'decoder_base_dim', 'in_channels', 'patch_size', 'out_channels', 'scale_factor_spatial', 'scale_factor_temporal'], '_class_name': 'AutoencoderKLWan', '_diffusers_version': '0.33.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--CalamitousFelicitousness--Anima-sdnext-diffusers/snapshots/587e3941c37ace6234f9c0daa5c908408652870a/vae'}) |
| scheduler | FlowMatchEulerDiscreteScheduler | None | None | None | 0 | 0 | FrozenDict({'num_train_timesteps': 1000, 'shift': 3.0, 'use_dynamic_shifting': False, 'base_shift': 0.5, 'max_shift': 1.15, 'base_image_seq_len': 256, 'max_image_seq_len': 4096, 'invert_sigmas': False, 'shift_terminal': None, 'use_karras_sigmas': False, 'use_exponential_sigmas': False, 'use_beta_sigmas': False, 'time_shift_type': 'exponential', 'stochastic_sampling': False, '_use_default_values': ['time_shift_type', 'max_image_seq_len', 'shift_terminal', 'use_beta_sigmas', 'base_image_seq_len', 'use_exponential_sigmas', 'max_shift', 'use_dynamic_shifting', 'use_karras_sigmas', 'stochastic_sampling', 'base_shift', 'invert_sigmas'], '_class_name': 'FlowMatchEulerDiscreteScheduler', '_diffusers_version': '0.37.0'}) |