--- title: Keeping grain and texture in an enhanced clip — Topaz Labs Proteus 4 | Runware Docs url: https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture description: "How to stop Topaz Proteus 4 from over-smoothing: prenoise before the pass, recoverOriginalDetail to blend the source back in, and grain with grainSize on the way out." --- ### [Introduction](https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture#introduction) A clip can be measurably cleaner and still look wrong. Noise reduction takes the grain out of skin along with the noise, detail reconstruction replaces a real surface with a plausible one, and what arrives is **the waxy look that reads as processed** long before a viewer could say why. Proteus carries three controls for that, and they act at **three different points in the pipeline**. `prenoise` adds noise before the enhancement runs, `recoverOriginalDetail` blends the source back into the result, and `grain` with `grainSize` lays a controlled grain over the finished frames after everything else. **Source**: [Watch video](https://runware.ai/docs/assets/source-sofa.DVPNpdyA.mp4) **Enhanced**: [Watch video](https://runware.ai/docs/assets/output-sofa.B7NKbLrO.mp4) The showroom pan is enhanced with all three in play. The leather keeps its grain and the throw keeps its weave, so the result reads as **a better capture of the same sofa** rather than a render of one. > [!WARNING] > These four values are weights like any other, so they carry the same rule: set `settings.enhancement.mode` to `relative` or `manual` in the same object, because `auto` accepts no weights. Their ranges are also different from the repair weights. `prenoise` and `grain` run **0 to 0.1**, `grainSize` runs **0 to 5**, and `recoverOriginalDetail` runs **0 to 1**, so 0.05 is a mid-scale value here rather than a nudge. ### [Adding noise before the pass](https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture#adding-noise-before-the-pass) `prenoise` puts a small amount of noise **into the input**, which sounds backwards until you look at what noise reduction does to a clean-but-soft frame. With nothing to work on, the `noise` weight covered in [tuning the enhancement weights](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights) flattens the fine variation that skin and fabric are made of. A little noise on the way in gives it something to remove other than the texture. **Source**: [Watch video](https://runware.ai/docs/assets/source-skincare.rVgvdlmU.mp4) *The noisy 480p source* **Auto**: [Watch video](https://runware.ai/docs/assets/output-skincare-auto.D29tVTRJ.mp4) *mode: auto* **Prenoise 0.06**: [Watch video](https://runware.ai/docs/assets/output-skincare-prenoise.Clnf4JVo.mp4) *mode: relative, prenoise 0.06* Skin is where this gets judged, and it has to be judged **at 100%**, because a cheek at page width looks smooth either way: ![A close-up crop of a cheek and fingertips, with faint mottling across the skin](https://runware.ai/docs/assets/crop-auto-skincare.BZ9HE53J_1X8ozx.jpg) *mode: auto · 100% crop* ![The same cheek crop, slightly smoother across the skin](https://runware.ai/docs/assets/crop-prenoise-skincare.CQqQsAut_ZwYY3C.jpg) *prenoise 0.06 · 100% crop* The two are close, and the `prenoise` take is **the smoother of the pair** rather than the more textured one. On this clip auto's noise reduction was already restrained, so there was no over-smoothing for the added input noise to fight, and that noise left with the rest of it. That is the shape of the control. `prenoise` is a **counterweight to aggressive denoising**, not a texture generator, so it only pays off where the denoiser is taking texture along with the noise. When a face comes back waxy, pull the `noise` weight down first, since that is the repair doing the smoothing, and reach for `prenoise` when you need the denoiser's strength on the rest of the frame but not its cost on skin. `prenoise` also tops out at **0.1**, which is a narrower range than the repair weights, so the 0.06 above is already past its middle. ### [Blending the source back in](https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture#blending-the-source-back-in) `recoverOriginalDetail` mixes **the original picture back into the enhanced one**, from 0 to 1. It is the answer to a different failure from `prenoise`: not smoothing, but invention. When detail reconstruction runs hard, the surface it builds is plausible rather than accurate, and a product that has to match a real object cannot afford plausible. **Source**: [Watch video](https://runware.ai/docs/assets/source-bakery.CtGWB4kv.mp4) *The 480p source* **Auto**: [Watch video](https://runware.ai/docs/assets/output-bakery-auto.DqvLZhTM.mp4) *mode: auto* **Recover 0.6**: [Watch video](https://runware.ai/docs/assets/output-bakery-recover.5mhQ-Zlp.mp4) *mode: relative, recoverOriginalDetail 0.6* The scoring on the loaves is the tell. Auto gives every crust a similar treatment, and the recovered take keeps the blistering each loaf actually had. **Raise it whenever the footage is evidence**, such as a product listing or a property walkthrough, where a customer compares the clip against the real thing. The trade is sharpness. The source is the softer of the two inputs being blended, so a high value pulls some of that softness back with the accuracy. ### [Grain on the way out](https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture#grain-on-the-way-out) `grain` and `grainSize` are a **finishing pass, not a repair**. Grain gets added after the enhancement, so it lands on the result rather than becoming something the model tries to remove. `grain` sets the amount, from 0 to 0.1, and `grainSize` sets how large each particle is, from 0 to 5. **No grain**: [Watch video](https://runware.ai/docs/assets/output-perfume-clean.CUXj6GLs.mp4) *mode: auto, no grain* **Fine grain**: [Watch video](https://runware.ai/docs/assets/output-perfume-fine.BkNs_SQX.mp4) *grain 0.04, grainSize 1.5* **Coarse grain**: [Watch video](https://runware.ai/docs/assets/output-perfume-coarse.BkhTVlMN.mp4) *grain 0.04, grainSize 4* Same amount, different particle. The fine setting reads as **film stock**, and the coarse one reads as a deliberate stylistic choice that a viewer will notice. Size matters more than amount for whether grain looks like an intention or an artefact. **TypeScript**: ```typescript import { createClient } from '@runware/sdk' const client = await createClient({ apiKey: process.env.RUNWARE_API_KEY }) await client.connect() const [result] = await client.run({ model: 'topazlabs:proteus@4', deliveryMethod: 'async', width: 1920, height: 1080, inputs: { video: 'https://vm.runware.ai/video/os/a14d18/ws/2/vi/7182a3b4-c5d6-4e7f-8091-a2b3c4d5e6f7.mp4' }, settings: { enhancement: { mode: 'relative', prenoise: 0.04, recoverOriginalDetail: 0.4, grain: 0.02, grainSize: 1.5 } } }) ``` **Python**: ```python import asyncio import os from runware import Runware async def main(): async with Runware(api_key=os.environ["RUNWARE_API_KEY"]) as client: results = await client.run({ "model": "topazlabs:proteus@4", "deliveryMethod": "async", "width": 1920, "height": 1080, "inputs": { "video": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/7182a3b4-c5d6-4e7f-8091-a2b3c4d5e6f7.mp4" }, "settings": { "enhancement": { "mode": "relative", "prenoise": 0.04, "recoverOriginalDetail": 0.4, "grain": 0.02, "grainSize": 1.5 } } }) asyncio.run(main()) ``` **cURL**: ```bash curl https://api.runware.ai/v1 \ -H "Authorization: Bearer $RUNWARE_API_KEY" \ -H "Content-Type: application/json" \ -d '[ { "taskType": "upscale", "taskUUID": "d1e2f3a4-5b6c-4d7e-8f9a-0b1c2d3e4f5a", "model": "topazlabs:proteus@4", "deliveryMethod": "async", "width": 1920, "height": 1080, "inputs": { "video": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/7182a3b4-c5d6-4e7f-8091-a2b3c4d5e6f7.mp4" }, "settings": { "enhancement": { "mode": "relative", "prenoise": 0.04, "recoverOriginalDetail": 0.4, "grain": 0.02, "grainSize": 1.5 } } } ]' ``` **CLI**: ```bash runware run topazlabs:proteus@4 \ deliveryMethod=async \ width=1920 \ height=1080 \ inputs.video=https://vm.runware.ai/video/os/a14d18/ws/2/vi/7182a3b4-c5d6-4e7f-8091-a2b3c4d5e6f7.mp4 \ settings.enhancement.mode=relative \ settings.enhancement.prenoise=0.04 \ settings.enhancement.recoverOriginalDetail=0.4 \ settings.enhancement.grain=0.02 \ settings.enhancement.grainSize=1.5 ``` **JSON**: ```json { "taskType": "upscale", "taskUUID": "d1e2f3a4-5b6c-4d7e-8f9a-0b1c2d3e4f5a", "model": "topazlabs:proteus@4", "deliveryMethod": "async", "width": 1920, "height": 1080, "inputs": { "video": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/7182a3b4-c5d6-4e7f-8091-a2b3c4d5e6f7.mp4" }, "settings": { "enhancement": { "mode": "relative", "prenoise": 0.04, "recoverOriginalDetail": 0.4, "grain": 0.02, "grainSize": 1.5 } } } ``` **Response**: ```json [ { "taskType": "upscale", "taskUUID": "d1e2f3a4-5b6c-4d7e-8f9a-0b1c2d3e4f5a", "videoUUID": "2c3d4e5f-6071-4829-a3b4-c5d6e7f80912", "videoURL": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/2c3d4e5f-6071-4829-a3b4-c5d6e7f80912.mp4" } ] ``` That payload is the showroom pan at the top of the page. Small values across all three, which is the shape most footage wants. ### [Grain and the delivery encode](https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture#grain-and-the-delivery-encode) Grain is **expensive to encode**. It is high-frequency detail spread across the whole frame, so it consumes bitrate that would otherwise go to the picture, and a platform encoder that runs out of budget turns it into blocking. A clip that looked right in the master can come back from a social platform looking noisy and blocky at once. Two habits keep it from going wrong. **Add grain last**, on the master you are actually delivering rather than on an intermediate that gets re-encoded. And **keep the amount low for platform delivery**, since a value that reads as texture on a local file can read as noise once the platform has had it. ### [Tips](https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture#tips) 1. **Match the control to the failure.** Flat, waxy surfaces call for `prenoise`. Detail that looks invented calls for `recoverOriginalDetail`. Neither is a grain problem, and `grain` will not fix either. 2. **Keep `prenoise` under 0.05 for most footage.** It protects texture at small values and becomes visible dither above the middle of its range. 3. **Raise `recoverOriginalDetail` when accuracy matters.** Product and property footage wants the real surface, even at some cost in sharpness. 4. **Set `grainSize` before you chase the amount.** Particle size decides whether grain reads as film or as noise, and the amount only decides how much of it there is. 5. **Add grain at the end of the chain.** It is a look, not a repair, so it belongs on the master you deliver rather than on a file that has another encode ahead of it. 6. **Check on the target platform.** Grain and social encoders fight each other, and the result that matters is the one after the platform has re-encoded it.