Info
andinsky 5.0 Image Lite is a line-up of 6B image generation models with the following capabilities:
1K resolution (1280x768, 1024x1024 and others).
High visual quality
Strong text-writing
Russian concepts understanding
https://github.com/kandinskylab/kandinsky-5
https://huggingface.co/kandinskylab/Kandinsky-5.0-T2I-Lite
https://habr.com/ru/companies/sberbank/articles/951800/
| transformer | Text Encoder | Text Encoder 2 | scheduler | tokenizer | tokenizer 2 | vae |
|---|---|---|---|---|---|---|
| Kandinsky5Transformer3DModel | Qwen2.5-VL-7B-Instruct | openai/clip-vit-large-patch14 | Euler FlowMatch | AutoProcessor Qwen2.5-VL | CLIPTokenizer | FLUX.1-dev vae |
Examples:
```python
>>> import torch
>>> from diffusers import Kandinsky5T2IPipeline
>>> # Available models:
>>> # kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers
>>> # kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers
>>> model_id = "kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers"
>>> pipe = Kandinsky5T2IPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
>>> pipe = pipe.to("cuda")
>>> prompt = "A cat and a dog baking a cake together in a kitchen."
>>> output = pipe(
... prompt=prompt,
... negative_prompt="",
... height=1024,
... width=1024,
... num_inference_steps=50,
... guidance_scale=3.5,
... ).frames[0]
```
Test 0 - Different seed variations
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, STEP50 | 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
| 4 | 8 | 16 | 32 | 50 | |
|---|---|---|---|---|---|
| CFG1 | |||||
| CFG2 | |||||
| CFG3 | |||||
| CFG4 | |||||
| CFG5 | |||||
| CFG6 | |||||
| CFG8 |
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.
| 8 | 16 | 20 | 32 | 50 | |
|---|---|---|---|---|---|
| CFG1 | |||||
| CFG2 | |||||
| CFG3 | |||||
| CFG4 | |||||
| CFG5 | |||||
| CFG6 | |||||
| CFG7 |
Test 3 - Legs
Prompt: 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 | |
|---|---|---|---|---|
| CFG2 | ||||
| CFG4 | ||||
| CFG6 | ||||
| CFG8 | ||||
| CFG10 |
Test 4 CivitAi profile cover generation
Prompt: image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand. Left bottom corner text "Flux.2 dev"
Parameters: Steps: 32| Size: 1600x400| Seed: 4014230639| CFG scale: 8
Prompt: with analog noise and glitches, CivitAi cover image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand.
Parameters: Steps: 32| Size: 1600x400| Seed: 2404111820| CFG scale: 3.5
Prompt: CivitAi cover image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand. Left bottom corner text "SD.Next + Flux.2 Dev", upper right corner text "Stable Diffusion at home"
Parameters: Steps: 50| Size: 1600x400| Seed: 978455805| CFG scale: 4
Prompt: LEGO style, CivitAi cover image with 5 canvases and one android robot painting on the 3rd canvas. first two is done with some futuristic images, last two is blank. robot is surprised look back at the camera. paint brush is in the robot hand. Left bottom corner text "SD.Next + Flux.2 Dev", upper right corner text "Stable Diffusion at home"
Parameters: Steps: 50| Size: 1600x400| Seed: 1179249187| CFG scale: 4
Test 5 - Empty prompts
1024x1024, Steps 50
seed 1 | seed 2 | seed 3 | seed 4 | seed 5 |
seed 6 | seed 7 | seed 8 | seed 9 | seed 10 |
seed 21 | seed 38 | seed 42 |
sweed 68 | seed 2025 |
Test 6 - Other Models cover
Test 7 - Art Prompts
System info
Config
{
}
Model info
Diffusers/kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers [25da1e82e6]
| Module | Class | Device | Dtype | Quant | Params | Modules | Config |
|---|---|---|---|---|---|---|---|
| transformer | Kandinsky5Transformer3DModel | xpu:0 | torch.float16 | None | 6022080576 | 1307 | FrozenDict({'in_visual_dim': 16, 'in_text_dim': 3584, 'in_text_dim2': 768, 'time_dim': 512, 'out_visual_dim': 16, 'patch_size': [1, 2, 2], 'model_dim': 2560, 'ff_dim': 10240, 'num_text_blocks': 2, 'num_visual_blocks': 50, 'axes_dims': [32, 48, 48], 'visual_cond': False, 'attention_type': 'regular', 'attention_causal': None, 'attention_local': None, 'attention_glob': None, 'attention_window': None, 'attention_P': None, 'attention_wT': None, 'attention_wW': None, 'attention_wH': None, 'attention_add_sta': None, 'attention_method': None, '_use_default_values': ['attention_wW', 'attention_wH', 'attention_add_sta', 'attention_P', 'attention_causal', 'attention_glob', 'attention_wT', 'attention_method', 'attention_window', 'attention_local'], '_class_name': 'Kandinsky5Transformer3DModel', '_diffusers_version': '0.33.0.dev0', '_name_or_path': 'kandinskylab/Kandinsky-5.0-T2I-Lite-sft-Diffusers'}) |
| vae | AutoencoderKL | cpu | torch.float16 | None | 83819683 | 241 | 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': '0.32.2', '_name_or_path': '/mnt/models/Diffusers/models--kandinskylab--Kandinsky-5.0-T2I-Lite-sft-Diffusers/snapshots/25da1e82e6adefdbc83c02a71f762287c5e471a4/vae'}) |
| text_encoder | Qwen2_5_VLForConditionalGeneration | xpu:0 | torch.float16 | None | 8292166656 | 763 | Qwen2_5_VLConfig { "architectures": [ "Qwen2_5_VLForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "float16", "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 128000, "max_window_layers": 28, "model_type": "qwen2_5_vl", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": 32768, "text_config": { "_name_or_path": "hunyuanvideo-community/HunyuanImage-2.1-Diffusers", "architectures": [ "Qwen2_5_VLForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "float16", "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 3584, "image_token_id": 151655, "initializer_range": 0.02, "intermediate_size": 18944, "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": 128000, "max_window_layers": 28, "model_type": "qwen2_5_vl_text", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": { "mrope_section": [ 16, 24, 24 ], "rope_type": "default", "type": "default" }, "rope_theta": 1000000.0, "sliding_window": null, "use_cache": true, "use_sliding_window": false, "video_token_id": 151656, "vision_end_token_id": 151653, "vision_start_token_id": 151652, "vision_token_id": 151654, "vocab_size": 152064 }, "tie_word_embeddings": false, "transformers_version": "4.57.3", "use_cache": true, "use_sliding_window": false, "vision_config": { "depth": 32, "dtype": "float16", "fullatt_block_indexes": [ 7, 15, 23, 31 ], "hidden_act": "silu", "hidden_size": 1280, "in_channels": 3, "in_chans": 3, "initializer_range": 0.02, "intermediate_size": 3420, "model_type": "qwen2_5_vl", "num_heads": 16, "out_hidden_size": 3584, "patch_size": 14, "spatial_merge_size": 2, "spatial_patch_size": 14, "temporal_patch_size": 2, "tokens_per_second": 2, "window_size": 112 }, "vision_token_id": 151654, "vocab_size": 152064 } |
| tokenizer | Qwen2VLProcessor | None | None | None | 0 | 0 | None |
| text_encoder_2 | CLIPTextModel | xpu:0 | torch.float16 | None | 123060480 | 152 | CLIPTextConfig { "attention_dropout": 0.0, "bos_token_id": 0, "dropout": 0.0, "dtype": "float16", "eos_token_id": 2, "hidden_act": "quick_gelu", "hidden_size": 768, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "projection_dim": 768, "transformers_version": "4.57.3", "vocab_size": 49408 } |
| tokenizer_2 | CLIPTokenizer | None | None | None | 0 | 0 | None |
| scheduler | FlowMatchEulerDiscreteScheduler | None | None |
