--- title: Tuning the enhancement weights — Topaz Labs Proteus 4 | Runware Docs url: https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights description: "How to tune Topaz Proteus 4 with settings.enhancement: what the auto, relative, and manual modes do, and how the compression, noise, details, and halo weights change a result." --- ### [Introduction](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#introduction) Every repair Proteus makes is a **numbered weight**, and `settings.enhancement.mode` decides who sets them. Left to itself the model measures the clip and fills in all ten. Name a weight yourself and you either shift the measurement or replace it, depending on the mode you asked for. This is what separates Proteus from an upscaler with a single quality dial. **The same footage can be treated four different ways** without regenerating anything, which matters when a house look has to repeat across a library rather than land once. **Source**: [Watch video](https://runware.ai/docs/assets/source-unboxing.Dy417n9Z.mp4) *The 480p source, compressed hard* **Auto**: [Watch video](https://runware.ai/docs/assets/output-unboxing-auto.CKTPBQ6P.mp4) *mode: auto, no weights* **Relative**: [Watch video](https://runware.ai/docs/assets/output-unboxing-relative.Cnpchopd.mp4) *mode: relative, compression +0.4* **Manual**: [Watch video](https://runware.ai/docs/assets/output-unboxing-manual.Dzp5LL8Q.mp4) *mode: manual, four weights set by hand* The four takes above are one source clip and one model. Only `settings.enhancement` changed between them. ### [The three modes](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#the-three-modes) `auto` is the default and the whole request when the footage is ordinary. The model reads the clip and applies the weights it estimates from it. It **accepts no weights at all**, so the moment you want to influence one you have to leave auto behind. `relative` keeps the estimates and **adds your value on top**, which is why its numbers stay small. A `compression` of 0.4 in relative mode means "whatever you measured, plus a bit more". `manual` ignores that negotiation and **uses your value as sent**, and any weight you leave out keeps the model's own value. Relative adapts to each clip, manual repeats itself exactly. **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/4d5e6f70-8192-4a3b-c4d5-e6f708192a3b.mp4' }, settings: { enhancement: { mode: 'relative', compression: 0.6 } } }) ``` **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/4d5e6f70-8192-4a3b-c4d5-e6f708192a3b.mp4" }, "settings": { "enhancement": { "mode": "relative", "compression": 0.6 } } }) 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": "e6f7a8b9-0c1d-4e2f-a3b4-c5d6e7f8a9b0", "model": "topazlabs:proteus@4", "deliveryMethod": "async", "width": 1920, "height": 1080, "inputs": { "video": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/4d5e6f70-8192-4a3b-c4d5-e6f708192a3b.mp4" }, "settings": { "enhancement": { "mode": "relative", "compression": 0.6 } } } ]' ``` **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/4d5e6f70-8192-4a3b-c4d5-e6f708192a3b.mp4 \ settings.enhancement.mode=relative \ settings.enhancement.compression=0.6 ``` **JSON**: ```json { "taskType": "upscale", "taskUUID": "e6f7a8b9-0c1d-4e2f-a3b4-c5d6e7f8a9b0", "model": "topazlabs:proteus@4", "deliveryMethod": "async", "width": 1920, "height": 1080, "inputs": { "video": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/4d5e6f70-8192-4a3b-c4d5-e6f708192a3b.mp4" }, "settings": { "enhancement": { "mode": "relative", "compression": 0.6 } } } ``` **Response**: ```json [ { "taskType": "upscale", "taskUUID": "e6f7a8b9-0c1d-4e2f-a3b4-c5d6e7f8a9b0", "videoUUID": "1b2c3d4e-5f60-4718-9a2b-3c4d5e6f7081", "videoURL": "https://vm.runware.ai/video/os/a14d18/ws/2/vi/1b2c3d4e-5f60-4718-9a2b-3c4d5e6f7081.mp4" } ] ``` > [!WARNING] > A weight without a mode is a **rejected request**. Sending `compression` while `mode` is `auto`, or while no mode is set at all, fails validation rather than falling back to a sensible default. Set `mode` to `relative` or `manual` in the same object as the weights. Each weight runs from **−1 to 1**, where 0 leaves that repair where the model put it, positive asks for more of it, and negative pulls it back below the estimate. **The weights are meant to travel together.** One request carries the whole set, the way the manual take in the hero does, and the repairs interact: clearing compression changes what the noise weight sees, and reducing noise changes what detail reconstruction has left to work with. The sections below take them one at a time so you can see what each contributes on its own, which is a way to learn them rather than a way to use them. ### [Reverting compression](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#reverting-compression) `compression` targets the **blocking and banding a low-bitrate encode leaves behind**, the square patches in flat areas and the stepped gradients in a sky. It is the first weight to reach for on anything that arrived through a web upload or a messaging app, because that damage sits on top of the picture rather than inside it. **Source**: [Watch video](https://runware.ai/docs/assets/source-cyclist.CYmOrLqg.mp4) *The 480p source, moderately compressed* **Auto**: [Watch video](https://runware.ai/docs/assets/output-cyclist-auto.BomDORUP.mp4) *mode: auto* **Compression +0.6**: [Watch video](https://runware.ai/docs/assets/output-cyclist-compression.BIkH7B5z.mp4) *mode: relative, compression +0.6* Auto removes the blocking on its own, and it is worth being clear about the third take: `compression +0.6` is close to indistinguishable from it. The estimate was already in the right place, and **a nudge above a good estimate is not where this weight pays off**. Motion-heavy footage like this starves the encoder first, so the damage is real, but auto reads that damage correctly without being told. ### [Reducing noise](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#reducing-noise) `noise` controls how hard the model **suppresses sensor noise and grain** before it rebuilds detail. Low-light footage is where it earns its keep, and also where it does the most damage, because the model cannot tell noise from the fine texture sitting underneath it. **Source**: [Watch video](https://runware.ai/docs/assets/source-hotel.BK-88oak.mp4) *The 480p source, noisy in the shadows* **Auto**: [Watch video](https://runware.ai/docs/assets/output-hotel-auto.Dt0TnGJJ.mp4) *mode: auto* **Noise +0.5**: [Watch video](https://runware.ai/docs/assets/output-hotel-noise.DlYYrAkp.mp4) *mode: relative, noise +0.5* The shadows go cleaner with the weight raised, and the linen loses some of its weave along with the grain. That trade is the reason `prenoise` exists, covered in [grain and texture](https://runware.ai/docs/models/topazlabs-proteus-4/guides/grain-and-texture). **Raise `noise` for shadow-heavy footage** and keep it low whenever fabric or skin carries the shot. ### [Recovering detail](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#recovering-detail) `details` sets **how much fine structure the model reconstructs** as it scales. It is the weight people reach for first and regret fastest, because detail reconstruction amplifies whatever else is in the frame, noise included. **Source**: [Watch video](https://runware.ai/docs/assets/source-coat.B95D_EOU.mp4) *The 480p source* **Auto**: [Watch video](https://runware.ai/docs/assets/output-coat-auto.B3nH-nGH.mp4) *mode: auto* **Details +0.6**: [Watch video](https://runware.ai/docs/assets/output-coat-details.CoxZamUO.mp4) *mode: relative, details +0.6* The twill weave and the topstitching arrive with the weight raised, which is exactly what a fashion listing needs and exactly what a noisy interior shot cannot afford. **Raise `details` on clean sources** and clear the noise first on dirty ones, in that order. ### [Clearing halos](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#clearing-halos) `halo` removes the **bright and dark fringes that ring high-contrast edges**. They are rarely in the original footage. They get baked in by an earlier sharpening pass or a broadcast encode, and they get worse when a model sharpens on top of them. **Source**: [Watch video](https://runware.ai/docs/assets/source-skyline.IaxqUJNG.mp4) *The 480p source, oversharpened before it got here* **Auto**: [Watch video](https://runware.ai/docs/assets/output-skyline-auto.CdHQvwFu.mp4) *mode: auto* **Halo +0.8**: [Watch video](https://runware.ai/docs/assets/output-skyline-halo.Df6FVv86.mp4) *mode: relative, halo +0.8* A halo is **one or two pixels wide**, so it vanishes at page width and the swapper above cannot show it to you. At 100% it is unmistakable: ![A close-up crop of dark diagonal beams against a bright sky, each beam outlined by a pale white line](https://runware.ai/docs/assets/crop-source-skyline.CW_QErct_Z8lXmH.jpg) *Source · 100% crop* ![The same crop after enhancement, with the beams meeting the sky cleanly and no pale outline](https://runware.ai/docs/assets/crop-auto-skyline.BiHfLg37_1OYY8Y.jpg) *Enhanced · 100% crop* The pale line running along both sides of every dark beam in the left crop is the halo. It **traces the shape of the edge**, which is what separates it from a reflection or a flare, and it sits on the bright side of a dark-to-light transition. On the right the beams meet the sky cleanly. Auto cleared it here without being asked, and the `halo +0.8` take in the swapper is barely distinguishable from the auto one. That is the honest shape of these weights: **pushing past an estimate that was already right buys very little**. The weight earns its keep when a fringe survives the default pass, which is likeliest on footage that has been sharpened more than once, and when you want to pull the correction back on a clip where auto softened an edge you wanted kept. > [!NOTE] > Judge this kind of repair **at 100%, not at page width**. Haloing, aliasing, and the difference between two weight settings all live at the pixel level, and a preview scaled to fit a browser window hides both the damage and the fix. ### [Relative or manual](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#relative-or-manual) Relative is the mode for **one clip at a time**. The estimates track whatever you feed it, so the same `+0.4` lands differently on a clean camera original and on a battered download, which is what you want when each source is its own problem. Manual is the mode for **a batch that has to match**. Identical numbers on every clip produce the same treatment regardless of what each one measures, which is how a library of episodes or a season of product videos ends up looking like one library rather than fifty decisions. The cost is that a clip whose damage differs from the rest gets the batch's treatment instead of its own. A practical order: run a representative clip in `auto`, look at what it needs more or less of, tune it in `relative` until it lands, then move those numbers into `manual` for the rest of the batch. ### [Tips](https://runware.ai/docs/models/topazlabs-proteus-4/guides/enhancement-weights#tips) 1. **Set the mode in the same object as the weights.** `mode` lives at `settings.enhancement.mode`, alongside the weights it governs, and a weight without `relative` or `manual` fails validation. 2. **Isolate while you diagnose, combine when you ship.** Move one weight per run while you are working out what a clip needs, since the repairs interact and a single change is the only way to attribute a result. The request you settle on carries the whole set at once. 3. **Keep relative values small.** They stack on top of an estimate that is already in the right area, so 0.2 to 0.5 is a nudge and 1.0 is usually an overcorrection. 4. **Clean before you sharpen.** Compression and noise come first, detail after. Raising `details` on a dirty source multiplies the dirt. 5. **Negative values are a tool.** A weight below 0 pulls a repair back under the estimate, which is the fix when auto reads film grain as noise or sharpens a soft-by-design shot. 6. **Move to manual for batches.** Tune on one representative clip, then send the same numbers to every clip in the set so the results match each other rather than their individual sources.