AI: Image to video in local: Difference between revisions
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
= Basic concepts = | = Basic concepts = | ||
== | == workflow == | ||
== noise level checkpoints == | |||
For WAN model, there are high and low are different checkpoints of the WAN model that are designed to handle different noise levels or phases in the diffusion process (start from noise and gradually refine into frames). | For WAN model, there are high and low are different [[AI definitions#Checkpoint|checkpoints]] of the WAN model that are designed to handle different noise levels or phases in the diffusion process (start from noise and gradually refine into frames). | ||
* A “high noise” model checkpoint is used for the '''earlier, high-noise phase''' of the generation process: when the latent is still very noisy, you need the model to do large corrections, heavy denoising, broad scene layout, motion establishment. | * A “high noise” model checkpoint is used for the '''earlier, high-noise phase''' of the generation process: when the latent is still very noisy, you need the model to do large corrections, heavy denoising, broad scene layout, motion establishment. | ||
| Line 15: | Line 14: | ||
== Safetensor == | == Safetensor == | ||
A safetensor is a small adapter that modify the main model’s weights at runtime (like LoRAs). It is a secure and fast file format for storing tensors, particularly large tensors like neural network weights. | A safetensor is a small adapter that modify the main model’s weights at runtime (like [[AI definitions#LoRA (Low-Rank Adaptation)|LoRAs]]). It is a secure and fast file format for storing tensors, particularly large tensors like neural network weights. | ||
== Quantification (Q) == | == Quantification (Q) == | ||
| Line 26: | Line 25: | ||
The '''higher number''' of fp is, '''higher quality''' will have the result and '''higher memory''' requirements will have. | The '''higher number''' of fp is, '''higher quality''' will have the result and '''higher memory''' requirements will have. | ||
== VAE == | |||
== Clip loader == | |||
== Model sampling == | |||
== Sampler == | |||
:: | :: | ||
[[Category:IT Resources]] | [[Category:IT Resources]] | ||
Revision as of 00:21, 31 October 2025
Basic concepts
workflow
noise level checkpoints
For WAN model, there are high and low are different checkpoints of the WAN model that are designed to handle different noise levels or phases in the diffusion process (start from noise and gradually refine into frames).
- A “high noise” model checkpoint is used for the earlier, high-noise phase of the generation process: when the latent is still very noisy, you need the model to do large corrections, heavy denoising, broad scene layout, motion establishment.
- A “low noise” model checkpoint is used for the later phase, when the latent is already mostly refined and only fine-details, motion smoothing and subtle transitions remain.
GGUF
GGUF is a file format for large language models (LLMs) that optimizes them for consumer hardware by allowing them to be compressed and run efficiently on standard CPUs. They are converted and quantized versions of large diffusion or language models.
Safetensor
A safetensor is a small adapter that modify the main model’s weights at runtime (like LoRAs). It is a secure and fast file format for storing tensors, particularly large tensors like neural network weights.
Quantification (Q)
If a model is quantified it is a compressed version of the original model where the numbers are stored with fewer bits (less precision). It saves memory and runs faster, at the cost of some quality.
The higher number of the quantification is, lower quality the result will have and lower memory requirements will have.
Floating point (fp)
It is a way of storing real numbers (like 3.14159) with high precision. Used for model weights and calculations.
The higher number of fp is, higher quality will have the result and higher memory requirements will have.