Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Building on HF
3
1
1
Denis
pollix
Follow
0 followers
Β·
2 following
AI & ML interests
None yet
Recent Activity
posted
an
update
about 4 hours ago
Shipped StudioMI300 for the AMD x lablab hackathon. One English sentence becomes a 30-second cinematic reel, end-to-end on a single AMD Instinct MI300X. Every model in the pipeline is Apache 2.0 or MIT. π¬ Director Agent β Qwen3.5-35B-A3B via vLLM with AITER MoE acceleration. Plans 6 shots, character bibles, music brief, per-shot voice-over. π¨ Character keyframes β FLUX.2 klein 4B reference editing. No LoRA training step. Identity stays consistent across shots by construction. ποΈ Animation β Wan2.2-I2V-A14B with ParaAttention FBCache (lossless 2x) and selective torch.compile on transformer_2 (another 1.2x). End-to-end Wan2.2 inference went from 25.9 min to 10.4 min per 720p clip. π Vision Critic β same Qwen3.5 checkpoint reloaded with a 10-label failure taxonomy (character drift, extras invade frame, camera ignored, walking backwards, hand artifact, wardrobe drift, neon glow leak, stylized AI look, random intimacy, object morphing). Bad clips auto-retry with targeted strategies. Up to 3 attempts. π΅ Music β ACE-Step v1 generates 30s instrumental from Director's brief. π£οΈ Narration β Kokoro-82M, 9 languages. Director picks language to match setting. Tokyo to Japanese, Paris to French, Mumbai to Hindi. The 192 GB HBM3 on MI300X is what lets four very different model architectures share one card sequentially. On a 24 GB consumer GPU this stack needs 4-5 separate machines wired together. Space (live infra restoring after hackathon close, pls like this space): https://huggingface.co/spaces/lablab-ai-amd-developer-hackathon/studiomi300 Code (Apache 2.0): https://github.com/bladedevoff/studiomi300 Special thanks to the FLUX, Wan2.2, ACE-Step and Kokoro teams for keeping serious generative AI open. The pipeline composes their work into something none of them alone can produce β a complete cinematic artifact from a single prompt. #AMDHackathon #ROCm #MI300X #OpenSource
new
activity
about 11 hours ago
lablab-ai-amd-developer-hackathon/studiomi300:
space: interactive replay demo β fast-forward 22s through real generation stages, with 6 real SF walk keyframes
new
activity
about 13 hours ago
lablab-ai-amd-developer-hackathon/studiomi300:
space: interactive replay demo
View all activity
Organizations
pollix
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a Space
1 day ago
Running
Agents
10
StudioMI300
π¬
10
One prompt β 30s cinematic reel on a single AMD MI300X
Load more