Script and Optimisation for 4Go VRAM, and launch script.#438
Open
N3oRay wants to merge 882 commits into
Open
Conversation
Amélioration respiration
clean code et stabilisation
clean code
Version very stable
version stable
Modification respiration
Stablisation mouvement
Version stable
version stable
rework
refacto
refacto
stablisation code
stabilisation code
Correctif convension
correctif
stabilisation code
stabilisation bruit
stable
stable
Version en DEV
“Motion Graph v5 – Cinematic Rig System” spine inertiel head lock caméra optionnel breathing séparé propre full skeleton graph (pas seulement bras) compatible diffusion latents (anti-blur garanti)
Cette version corrige ça implicitement via : velocity smoothing cohérent anchor EMA stable drift filtré
Correctif important
Stabilisation hanches inconnues
clean code
Finalisation
clean debug
Fix Mouth
Version casi stable
Good version
model +
Refacto, clean, and coment
Optimisation and clean code
Color adaptative fixe
Apply Mouth in dev
DEv in progresse
Version stable
Version stable
Version stable
update model
Version final
Finalisation motion
Version final optimisé
correctif final
Stabilisation Mouth grand format
Version final
Optimal
Finalisation animation bouche
Optimisation simple
Refacto complet
Hair and décor optimised
Stabilisation hair
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Fast Latent Interpolation Movie Generator
A high-performance, GPU-optimized video generation pipeline based on Stable Diffusion and AnimateDiff. Supports smooth latent interpolation, prompt-guided generation, motion scripts, tile functions with overlap, and automatic video export. Designed to run efficiently on 4GB VRAM.
Features
🔹 Load Configuration – load_config
🔹 Load Models – safe_load_unet, safe_load_vae_stable, etc.
🔹 Generate Latents – generate_latents_robuste
🔹 Decode Latents – decode_latents_to_image_auto
🔹 Export Video – automatic compilation with ffmpeg
Pipeline Overview
This modular and robust pipeline allows you to:
Load one or more models (UNet, VAE, Scheduler, Motion Module).
Encode latent images for video generation.
Generate animated frames guided by prompts.
Perform smooth interpolation between multiple images.
Save each frame automatically.
Compile frames into a video automatically using ffmpeg.
Pause interactively during generation for user control.
Optimized for speed, efficiency, and low VRAM usage, making it suitable for quick experimentation and high-quality output.