Since spending a lot of time recently with SDXL I’ve since made my way back to SD 1.5
While the models overall have less fidelity. There is just no comparing to the current motion models we have available for animatediff with 1.5 models.
To date this is one of my favorite pieces. Not because I think it’s even the best it can be. But because the workflow adjustments unlocked some very important ideas I can’t wait to try out.
Performance by @silkenkelly and @itxtheballerina on IG
The power output of a light source is measured using the unit of watts W. This is a direct measure to calculate how much power the light is going to drain from your socket and it is not relatable to the light brightness itself.
The amount of energy emitted from it per second. That energy comes out in a form of photons which we can crudely represent with rays of light coming out of the source. The higher the power the more rays emitted from the source in a unit of time.
Not all energy emitted is visible to the human eye, so we often rely on photometric measurements, which takes in account the sensitivity of human eye to different wavelenghts
One problem with sRGB is that in a gradient between blue and white, it becomes a bit purple in the middle of the transition. That’s because sRGB really isn’t created to mimic how the eye sees colors; rather, it is based on how CRT monitors work. That means it works with certain frequencies of red, green, and blue, and also the non-linear coding called gamma. It’s a miracle it works as well as it does, but it’s not connected to color perception. When using those tools, you sometimes get surprising results, like purple in the gradient.
There were also attempts to create simple models matching human perception based on XYZ, but as it turned out, it’s not possible to model all color vision that way. Perception of color is incredibly complex and depends, among other things, on whether it is dark or light in the room and the background color it is against. When you look at a photograph, it also depends on what you think the color of the light source is. The dress is a typical example of color vision being very context-dependent. It is almost impossible to model this perfectly.
I based Oklab on two other color spaces, CIECAM16 and IPT. I used the lightness and saturation prediction from CIECAM16, which is a color appearance model, as a target. I actually wanted to use the datasets used to create CIECAM16, but I couldn’t find them.
IPT was designed to have better hue uniformity. In experiments, they asked people to match light and dark colors, saturated and unsaturated colors, which resulted in a dataset for which colors, subjectively, have the same hue. IPT has a few other issues but is the basis for hue in Oklab.
In the Munsell color system, colors are described with three parameters, designed to match the perceived appearance of colors: Hue, Chroma and Value. The parameters are designed to be independent and each have a uniform scale. This results in a color solid with an irregular shape. The parameters are designed to be independent and each have a uniform scale. This results in a color solid with an irregular shape. Modern color spaces and models, such as CIELAB, Cam16 and Björn Ottosson own Oklab, are very similar in their construction.
By far the most used color spaces today for color picking are HSL and HSV, two representations introduced in the classic 1978 paper “Color Spaces for Computer Graphics”. HSL and HSV designed to roughly correlate with perceptual color properties while being very simple and cheap to compute.
Today HSL and HSV are most commonly used together with the sRGB color space.
One of the main advantages of HSL and HSV over the different Lab color spaces is that they map the sRGB gamut to a cylinder. This makes them easy to use since all parameters can be changed independently, without the risk of creating colors outside of the target gamut.
The main drawback on the other hand is that their properties don’t match human perception particularly well.
Reconciling these conflicting goals perfectly isn’t possible, but given that HSV and HSL don’t use anything derived from experiments relating to human perception, creating something that makes a better tradeoff does not seem unreasonable.
With this new lightness estimate, we are ready to look into the construction of Okhsv and Okhsl.
In the retina, photoreceptors, bipolar cells, and horizontal cells work together to process visual information before it reaches the brain. Here’s how each cell type contributes to vision:
The Manuka rendering architecture has been designed in the spirit of the classic reyes rendering architecture. In its core, reyes is based on stochastic rasterisation of micropolygons, facilitating depth of field, motion blur, high geometric complexity,and programmable shading.
This is commonly achieved with Monte Carlo path tracing, using a paradigm often called shade-on-hit, in which the renderer alternates tracing rays with running shaders on the various ray hits. The shaders take the role of generating the inputs of the local material structure which is then used bypath sampling logic to evaluate contributions and to inform what further rays to cast through the scene.
Over the years, however, the expectations have risen substantially when it comes to image quality. Computing pictures which are indistinguishable from real footage requires accurate simulation of light transport, which is most often performed using some variant of Monte Carlo path tracing. Unfortunately this paradigm requires random memory accesses to the whole scene and does not lend itself well to a rasterisation approach at all.
Manuka is both a uni-directional and bidirectional path tracer and encompasses multiple importance sampling (MIS). Interestingly, and importantly for production character skin work, it is the first major production renderer to incorporate spectral MIS in the form of a new ‘Hero Spectral Sampling’ technique, which was recently published at Eurographics Symposium on Rendering 2014.
Manuka propose a shade-before-hit paradigm in-stead and minimise I/O strain (and some memory costs) on the system, leveraging locality of reference by running pattern generation shaders before we execute light transport simulation by path sampling, “compressing” any bvh structure as needed, and as such also limiting duplication of source data.
The difference with reyes is that instead of baking colors into the geometry like in Reyes, manuka bakes surface closures. This means that light transport is still calculated with path tracing, but all texture lookups etc. are done up-front and baked into the geometry.
The main drawback with this method is that geometry has to be tessellated to its highest, stable topology before shading can be evaluated properly. As such, the high cost to first pixel. Even a basic 4 vertices square becomes a much more complex model with this approach.
Manuka use the RenderMan Shading Language (rsl) for programmable shading [Pixar Animation Studios 2015], but we do not invoke rsl shaders when intersecting a ray with a surface (often called shade-on-hit). Instead, we pre-tessellate and pre-shade all the input geometry in the front end of the renderer.
This way, we can efficiently order shading computations to sup-port near-optimal texture locality, vectorisation, and parallelism. This system avoids repeated evaluation of shaders at the same surface point, and presents a minimal amount of memory to be accessed during light transport time. An added benefit is that the acceleration structure for ray tracing (abounding volume hierarchy, bvh) is built once on the final tessellated geometry, which allows us to ray trace more efficiently than multi-level bvhs and avoids costly caching of on-demand tessellated micropolygons and the associated scheduling issues.
For the shading reasons above, in terms of AOVs, the studio approach is to succeed at combining complex shading with ray paths in the render rather than pass a multi-pass render to compositing.
For the Spectral Rendering component. The light transport stage is fully spectral, using a continuously sampled wavelength which is traced with each path and used to apply the spectral camera sensitivity of the sensor. This allows for faithfully support any degree of observer metamerism as the camera footage they are intended to match as well as complex materials which require wavelength dependent phenomena such as diffraction, dispersion, interference, iridescence, or chromatic extinction and Rayleigh scattering in participating media.
As opposed to the original reyes paper, we use bilinear interpolation of these bsdf inputs later when evaluating bsdfs per pathv ertex during light transport4. This improves temporal stability of geometry which moves very slowly with respect to the pixel raster
In terms of the pipeline, everything rendered at Weta was already completely interwoven with their deep data pipeline. Manuka very much was written with deep data in mind. Here, Manuka not so much extends the deep capabilities, rather it fully matches the already extremely complex and powerful setup Weta Digital already enjoy with RenderMan. For example, an ape in a scene can be selected, its ID is available and a NUKE artist can then paint in 3D say a hand and part of the way up the neutral posed ape.
We called our system Manuka, as a respectful nod to reyes: we had heard a story froma former ILM employee about how reyes got its name from how fond the early Pixar people were of their lunches at Point Reyes, and decided to name our system after our surrounding natural environment, too. Manuka is a kind of tea tree very common in New Zealand which has very many very small leaves, in analogy to micropolygons ina tree structure for ray tracing. It also happens to be the case that Weta Digital’s main site is on Manuka Street.
Colour is an open-source Python package providing a comprehensive number of algorithms and datasets for colour science. It is freely available under the BSD-3-Clause terms.
Physically-based shading means leaving behind phenomenological models, like the Phong shading model, which are simply built to “look good” subjectively without being based on physics in any real way, and moving to lighting and shading models that are derived from the laws of physics and/or from actual measurements of the real world, and rigorously obey physical constraints such as energy conservation.
For example, in many older rendering systems, shading models included separate controls for specular highlights from point lights and reflection of the environment via a cubemap. You could create a shader with the specular and the reflection set to wildly different values, even though those are both instances of the same physical process. In addition, you could set the specular to any arbitrary brightness, even if it would cause the surface to reflect more energy than it actually received.
In a physically-based system, both the point light specular and the environment reflection would be controlled by the same parameter, and the system would be set up to automatically adjust the brightness of both the specular and diffuse components to maintain overall energy conservation. Moreover you would want to set the specular brightness to a realistic value for the material you’re trying to simulate, based on measurements.
Physically-based lighting or shading includes physically-based BRDFs, which are usually based on microfacet theory, and physically correct light transport, which is based on the rendering equation (although heavily approximated in the case of real-time games).
It also includes the necessary changes in the art process to make use of these features. Switching to a physically-based system can cause some upsets for artists. First of all it requires full HDR lighting with a realistic level of brightness for light sources, the sky, etc. and this can take some getting used to for the lighting artists. It also requires texture/material artists to do some things differently (particularly for specular), and they can be frustrated by the apparent loss of control (e.g. locking together the specular highlight and environment reflection as mentioned above; artists will complain about this). They will need some time and guidance to adapt to the physically-based system.
On the plus side, once artists have adapted and gained trust in the physically-based system, they usually end up liking it better, because there are fewer parameters overall (less work for them to tweak). Also, materials created in one lighting environment generally look fine in other lighting environments too. This is unlike more ad-hoc models, where a set of material parameters might look good during daytime, but it comes out ridiculously glowy at night, or something like that.
Here are some resources to look at for physically-based lighting in games:
SIGGRAPH 2013 Physically Based Shading Course, particularly the background talk by Naty Hoffman at the beginning. You can also check out the previous incarnations of this course for more resources.
And of course, I would be remiss if I didn’t mention Physically-Based Rendering by Pharr and Humphreys, an amazing reference on this whole subject and well worth your time, although it focuses on offline rather than real-time rendering.
DISCLAIMER – Links and images on this website may be protected by the respective owners’ copyright. All data submitted by users through this site shall be treated as freely available to share.
