Versions Compared

Key

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


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://habr.com/ru/companies/sberbank/articles/951800/

transformerText EncoderText Encoder 2schedulertokenizertokenizer 2vae
Kandinsky5Transformer3DModelQwen2.5-VL-7B-Instructopenai/

...

clip-vit-large-patch14Euler FlowMatchAutoProcessor Qwen2.5-VLCLIPTokenizerFLUX.1-dev vae
Code Block
    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]
        ```
Code Block
prompt = " 

Test 0 - Different seed variations

...