You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Anima in diffusers

Anima weights in diffusers environment. Copy the "anima-preview.safetensors" to an the "transformer" directory.

I'm aware that another diffusers compatible code has been uploaded elsewhere. However, if the llm_adapter cannot handle padded tokens, then the implementation was incorrect. This repo relies on the assumption that the adapter model can handle padded input tokens; as it should.

Inference

from cosmos_predict2 import CosmosPredict2Pipeline

pipeline = CosmosPredict2Pipeline('/path/to/this/bundle')
# Unlike in diffusers, we don't call a long forward function here.
qwen_embeds, t5_input_ids = pipeline.prepare_text_embeds(text)
crossattn_emb = pipeline.transformer.preprocess_text_embeds(qwen_embeds, t5_input_ids)
pipeline.transformer.to('cuda')
# Sampling with FlowMatchEulerDiscreteScheduler.
output = pipeline.sample_fm(
    torch.randn((1, 16, 1, 64, 64), device='cuda', dtype=torch.bfloat16),
    num_inference_steps=30,
    crossattn_emb=crossattn_emb.to('cuda'),
)
pipeline.vae.to('cuda')
image = pipeline.decode_vae(output)

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support