Instructions to use siraxe/Venom_transformation_H3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use siraxe/Venom_transformation_H3 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import export_to_video # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("siraxe/Venom_transformation_H3") prompt = "For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced.subject_definitions:<Subject 1> Large t-rex dinosaur standing surfing on a board in the sea<Subject 2> Large t-rex dinosaur in venom style form , surfing on a board in the sea.environment: Water wave in the background , in sea matching <Picture 1> color temperature.camera: Static medium shot that transitions to a wide shot of (S2) as transformation completes.integrated_multimodal_description: Fast paced action shot . Dynamic action scene. Secondary black goo head grows on (S1). (S1) while surfing begins to contort his facial features and body, his expression shifting into a grimace as the transformation progresses. He holds his mouth closed as secondary jaw with sharp teeth start grow on his neck and on top of his head, then closing his mouth from top and bottom closing on his real head , extra jaw merging with his real jaw. His skin darkens and stretches, revealing (S2)’s black symbiote form emerging from his body. (S2) rises fully formed, snarling with an open mouth and glowing eyes, as the camera holds steady on his transformed face while still riding the wave.overall_soundscape: Deep bass rumble, sharp metallic screech during transformation.non_diegetic_music: N/Aending: (S2) stands fully transformed into dinosaur covered by venom facing forward, as the camera slowly zooms out to reveal his full menacing silhouette against the water wave." output = pipe(prompt=prompt).frames[0] export_to_video(output, "output.mp4") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
Welcome to the community
The community tab is the place to discuss and collaborate with the HF community!