Image-Text-to-Video
Diffusers
Safetensors
MiniMax H3
modular-diffusers
ref2va
fl2va
Merge
synchronized-audio-video
experimental
Instructions to use diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("diffusers-modular/MiniMax-H3-Pruned-Ref-Delta-Fused-r1024", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -114,8 +114,6 @@ ships a `MiniMaxH3PrunedTransformer3DModel` whose AdaLN is 8 wide, where the sto
|
|
| 114 |
5. **Keep the AdaLN affine map.** `adaln_basis` / `adaln_mean` ship as buffers, so LoRAs trained on the released
|
| 115 |
2688-wide AdaLN still project onto this 8-wide one.
|
| 116 |
|
| 117 |
-
Verified by re-downloading this repo and generating: bit-identical (`torch.equal` on video and audio latents) to the
|
| 118 |
-
local build it was made from.
|
| 119 |
|
| 120 |
## Measured
|
| 121 |
|
|
|
|
| 114 |
5. **Keep the AdaLN affine map.** `adaln_basis` / `adaln_mean` ship as buffers, so LoRAs trained on the released
|
| 115 |
2688-wide AdaLN still project onto this 8-wide one.
|
| 116 |
|
|
|
|
|
|
|
| 117 |
|
| 118 |
## Measured
|
| 119 |
|