daniel/h3-blackwell-runtime
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Decode preview VAE in inference mode

Browse source
This commit is contained in:
Daniel Maddern 2026-08-13 23:29:29 +07:00
parent d6e83440c3
commit 5f68f1dce9
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
tools/direct_t2v_preview.py
View file

@ -47,7 +47,8 @@ if args.model_timesteps_capture is not None:
]
latent = sample_video_res_multistep(model, H3PromptPacker(checkpoint), text, video, audio, steps=args.steps, model_timesteps=model_timesteps)
vae = MiniMaxH3VideoVAE.from_safetensors("/vae/minimax_h3_video_vae_fp16.safetensors", device="cuda").eval()
pixels = vae.decode(latent.to(next(vae.parameters()).dtype))[:, :, :frames]
with torch.inference_mode():
pixels = vae.decode(latent.to(next(vae.parameters()).dtype))[:, :, :frames]
pixels = ((pixels[0].permute(1, 2, 3, 0).clamp(-1, 1) + 1) * 127.5).to(torch.uint8).cpu()
args.output.parent.mkdir(parents=True, exist_ok=True)
raw = args.output.with_suffix(".rgb")