Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

Info

Image Added

https://huggingface.co/AIDC-AI/Ovis-Image-7B

...

Test 0 - Different seed variations

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

Parameters: Steps: 50| Size: 1024x1024| Seed: 1620085323| CFG scale: 5| App: SD.Next| Version: d7eb90e| Pipeline: OvisImagePipeline| Operations: txt2img| Model: Ovis-Image-7B

285H Time: 9m 19.20s | total 561.76 pipeline 556.42 decode 2.72 callback 2.18 gc 0.38 | GPU 21078 MB 17% | RAM 30.89 GB 25%

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, STEP50Seed: 1620085323Seed:1931701040Seed:4075624134Seed:2736029172
bookshop girl

Image Added

Image Added

Image Added

Image Added

hand and face

Image Added

Image Added

Image Added

Image Added

legs and shoes

Image Added

Image Added

Image Added

Image Added


Test 1 - Bookshop

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

Parameters: Steps: 50| Size: 1024x1024| Seed: 2736029172| CFG scale: 5| App: SD.Next| Version: d7eb90e| Pipeline: OvisImagePipeline| Operations: txt2img| Model: Ovis-Image-7B

285H Time: 9m 16.08s | total 558.72 pipeline 554.54 callback 2.35 decode 1.52 gc 0.29 | GPU 21078 MB 17% | RAM 31.24 GB 25%



816203250
CFG1

Image Added

Image Added

Image Added

Image Added

Image Added

CFG2

Image Added

Image Added

Image Added

Image Added

Image Added

CFG3

Image Added

Image Added

Image Added

Image Added

Image Added

CFG4

Image Added

Image Added

Image Added

Image Added

Image Added

CFG5

Image Added

Image Added

Image Added

Image Added

Image Added

CFG6

Image Added

Image Added

Image Added

Image Added

Image Added

CFG7

Image Added

Image Added

Image Added

Image Added

Image Added

CFG8

Image Added

Image Added

Image Added

Image Added

Image Added


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.

Parameters: Steps: 16| Size: 1024x1024| Seed: 4075624134| CFG scale: 5| App: SD.Next| Version: d7eb90e| Pipeline: OvisImagePipeline| Operations: txt2img| Model: Ovis-Image-7B

285H Time: 2m 58.98s | total 180.04 pipeline 177.45 decode 1.51 callback 0.78 gc 0.28 | GPU 21078 MB 17% | RAM 31.23 GB 25%



816
20
32
50
64
CFG1
CFG2

Image Added

Image Added

Image Added

Image Added

CFG3
CFG4

Image Added

Image Added

Image Added

Image Added

CFG5
CFG6CFG7

Image Added

Image Added

Image Added

Image Added

CFG7

Image Added

Image Added

Image Added

Image Added

CFG9

Image Added

Image Added

Image Added

Image Added

Test 3 - Legs

Prompt: Prompt: Generate 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: 1024x1024| Seed: 1931701040| CFG scale: 5| App: SD.Next| Version: d7eb90e| Pipeline: OvisImagePipeline| Operations: txt2img| Model: Ovis-Image-7B

285H Time: 5m 56.50s | total 358.27 pipeline 354.97 decode 1.52 callback 1.48 gc 0.29 | GPU 21078 MB 17% | RAM 31.29 GB 25%



8163264
CFG2
CFG1

Image Added

Image Added

Image Added

Image Added

CFG3

Image Added

Image Added

Image Added

Image Added

CFG5

Image Added

Image Added

Image Added

Image Added

CFG7

Image Added

Image Added

Image Added

Image Added

CFG11

Image Added

Image Added

Image Added

Image Added

CFG4CFG6CFG8CFG10

Test 4 CivitAi profile cover generation

...

Test 5 - Empty prompts


1024x1024, Steps 50

Image Added

seed 1

Image Added

seed 2

Image Added

seed 3

Image Added

seed 4

Image Added

seed 5

Image Added

seed 6

Image Added

seed 7

Image Added

seed 8

Image Added

seed 9

Image Added

seed 10

Image Added

seed 21

Image Added

seed 38

Image Added

seed 42

 Image Added

seed 68

Image Added

seed 2025

Test 6 - Other Models cover

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

Test 7 - Art Prompts

Test 8 - Search for cover image

System info

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added


Compare Art to Z Image turbo

Ovis Image (7B)Z Image Turbo (6B) - 90 sec on Intel 285H for 9 steps

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

Image AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage AddedImage Added

System info

Code Block
Sat Dec 27 16:49:13 2025
app: sdnext.git updated: 2025-12-26 hash: d7eb90eb8 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 Torch: 2.9.1+xpu
device: Intel(R) Arc(TM) Graphics (1) ipex: 
ram: free:114.21 used:8.86 total:123.07
xformers:  diffusers: 0.36.0.dev0 transformers: 4.57.3
active: xpu dtype: torch.bfloat16 vae: torch.bfloat16 unet: torch.bfloat16
base: Diffusers/AIDC-AI/Ovis-Image-7B [ac8fb1056c] refiner: none vae: none te: none unet: none
ipex native none Scaled-Dot-Product
Code Block

.


Config

Code Block
{
  "sd_model_checkpoint": "Diffusers/AIDC-AI/Ovis-Image-7B [ac8fb1056c]",
  "diffusers_offload_mode": "none",
  "huggingface_token": "hf_..FraU",
  "diffusers_version": "f6b6a7181eb44f0120b29cd897c129275f366c2a",
  "sd_checkpoint_hash": null,
  "model_qwen_layers": 6
}


Model info

AIDC-AI/Ovis-Image-7B [ac8fb1056c]
ModuleClassDeviceDtypeQuantParamsModulesConfig
vaeAutoencoderKLxpu:0torch.bfloat16None83819683241

FrozenDict({'in_channels': 3, 'out_channels': 3, 'down_block_types': ['DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D', 'DownEncoderBlock2D'], 'up_block_types': ['UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D', 'UpDecoderBlock2D'], 'block_out_channels': [128, 256, 512, 512], 'layers_per_block': 2, 'act_fn': 'silu', 'latent_channels': 16, 'norm_num_groups': 32, 'sample_size': 1024, 'scaling_factor': 0.3611, 'shift_factor': 0.1159, 'latents_mean': None, 'latents_std': None, 'force_upcast': True, 'use_quant_conv': False, 'use_post_quant_conv': False, 'mid_block_add_attention': True, '_class_name': 'AutoencoderKL', '_diffusers_version': '0.30.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--AIDC-AI--Ovis-Image-7B/snapshots/ac8fb1056c6df0b22901ddcabc965336eb9bdc41/vae'})

text_encoderQwen3Modelxpu:0torch.bfloat16None1720574976425

Qwen3Config { "_attn_implementation_autoset": true, "architectures": [ "Qwen3Model" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "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": 40960, "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, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "4.57.3", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }

tokenizerQwen2TokenizerFastNoneNoneNone00

None

transformerOvisImageTransformer2DModelxpu:0torch.bfloat16None7370449728635

FrozenDict({'patch_size': 1, 'in_channels': 64, 'out_channels': None, 'num_layers': 6, 'num_single_layers': 27, 'attention_head_dim': 128, 'num_attention_heads': 24, 'joint_attention_dim': 2048, 'axes_dims_rope': [16, 56, 56], '_class_name': 'OvisImageTransformer2DModel', '_diffusers_version': '0.36.0.dev0', '_name_or_path': '/mnt/models/Diffusers/models--AIDC-AI--Ovis-Image-7B/snapshots/ac8fb1056c6df0b22901ddcabc965336eb9bdc41/transformer'})

schedulerFlowMatchEulerDiscreteSchedulerNoneNoneNone00

FrozenDict({'num_train_timesteps': 1000, 'shift': 3.0, 'use_dynamic_shifting': True, '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': ['invert_sigmas', 'use_exponential_sigmas', 'use_karras_sigmas', 'time_shift_type', 'shift_terminal', 'stochastic_sampling', 'use_beta_sigmas'], '_class_name': 'FlowMatchEulerDiscreteScheduler', '_diffusers_version': '0.30.0.dev0'})