thread for ideas on lora/workflow/ features
upscaler is desperately needed. integrated or passed in with --lora or however that can work
https://huggingface.co/LBH-123-AI/Minimax_h3_latent_Upscaler
Purpose
This model is designed to accelerate high-resolution H3 video generation:
- Generate video at low resolution — far fewer latent tokens, much faster.
- Upscale the latent in-place with this learned upscaler.
- Re-sample / refine at the target resolution to recover detail.
By skipping the expensive decode → pixel upscale → encode round-trip through Minimax H3's heavy ~5B-parameter VAE, this pipeline saves a significant amount of generation time. It also avoids the ghosting / double-image artifacts that naive latent interpolation (bilinear/bicubic) introduces.
MiniMax H3 Realism People LoRA
Trigger word: r34l1sm
A LoRA adapter for MiniMax H3 specialized in realistic people: faces that hold up in close-up, natural skin texture, believable expressions and gestures, film-style lighting and documentary camera movement.
LoRA Spatial & Physics (MiniMax-H3)
LoRA, a spatial reasoning and physical logic model, is trained on MiniMax-H3 (Comfy-Org/MiniMax-H3) and enables the model to learn the spatial relationships and physical motions of pure objects (collision, stacking, falling, occlusion, etc.).
https://huggingface.co/Jojocodex/minimax-h3-spatial-physics-lora
TX-2.5 22B IC-LoRA Pixel Spatial Upscaler
https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler
How It Works
The model is an in-context LoRA: instead of taking only a text prompt, it also consumes a reference video in context alongside the noisy latents being denoised. During training, the reference is a downscaled version of the target clip, so the model learns to map a low-resolution reference onto a higher-resolution rendering of the same scene.
At inference the reference is your low-resolution clip. The model does not upsample it pixel-wise; it re-renders the scene at the higher resolution, inventing plausible fine detail (texture, edges, micro-contrast) that was never present in the reference. Composition, motion and subject identity are carried over from the reference, while high-frequency detail is generated.