import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("CalamitousFelicitousness/Anima-Preview-3-sdnext-diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Anima Preview 3 (SD.Next Diffusers Conversion)
Diffusers-format conversion of Anima Preview 3 for use with SD.Next.
Original model: circlestone-labs/Anima
Changes from Preview 2
- Extended training at 1024 resolution
- Expanded dataset coverage for less common artists (50-100 post count)
Architecture
- Transformer: CosmosTransformer3DModel (2B params, 28 layers)
- Text Encoder: Qwen3-0.6B (replacing Cosmos T5-11B)
- LLM Adapter: Custom cross-attention adapter bridging Qwen3 to the transformer
- VAE: AutoencoderKLWan
- Downloads last month
- 885