{
 "schema_version": 1,
 "generated": "2026-10-20",
 "id": "worldbench-diffusionopsd--post-train-sd35-on-image-reward",
 "repo": "worldbench/DiffusionOPSD",
 "repo_url": "https://github.com/worldbench/DiffusionOPSD",
 "repo_slug": "worldbench-diffusionopsd",
 "title": "Post-train SD3.5-M toward a chosen image reward",
 "page_title": "How to post-train SD3.5-M toward a chosen image reward with Diffusion OPSD",
 "summary": "Fine-tune SD3.5-M with Diffusion OPSD using a reward preset and measure the held-out score.",
 "who": "An ML engineer with a multi-GPU Linux box who wants to improve SD3.5-M outputs for a specific aesthetic or preference score.",
 "problem": "Reward-guided diffusion training usually sees only a final image score, so intermediate denoising steps get weak supervision.",
 "outcome": "A DiffusionOPSD-trained SD3.5-M checkpoint and training logs for one reward objective, ready to compare against the README's reported held-out results.",
 "steps": [
  "Run `git clone https://github.com/worldbench/DiffusionOPSD.git` and `cd DiffusionOPSD`.",
  "Run `conda create -n diffusionopsd python=3.11 -y` and `conda activate diffusionopsd`.",
  "Run `pip install -e \".[rewards]\"` and then `pip install --no-deps 'image-reward==1.5'`.",
  "Set `export REWARD_CKPT_PATH=\"$PWD/reward_ckpts\"` and run `bash scripts/download_reward_weights.sh`.",
  "Accept the SD3.5-M license on Hugging Face and authenticate, then start a preset with `bash scripts/train_public.sh sd35 hpsv3` (replace hpsv3 with a standard reward preset such as PickScore, which is an inferred choice)."
 ],
 "agent_prompt": "Using the repo worldbench/DiffusionOPSD, set up the environment and run the SD3.5-M training preset for <reward name>. Report the training command used, the reward checkpoint path, and the final evaluation score for <reward name>. Verify that scripts/download_reward_weights.sh completed without errors before starting training.",
 "agents": [
  "any"
 ],
 "difficulty": "Advanced",
 "time": "1 day",
 "basis": "readme",
 "caveat": "The README says a recent Linux environment with CUDA GPUs is required for training, so this will not run on a laptop without suitable GPUs.",
 "category": "Research",
 "tags": [
  "Research"
 ],
 "lang": "python",
 "requirements": [
  "A recent Linux machine with CUDA GPUs (eight-GPU profiles are reported in the README)",
  "Python 3.10 or 3.11 and conda",
  "A Hugging Face account that has accepted the SD3.5-M license, for the gated model",
  "Enough disk space for model weights, reward checkpoints, and the Pick-a-Pic prompt manifest"
 ],
 "risk": "none",
 "seen_in_the_wild": false,
 "mentioned_publicly": false,
 "risks": [
  {
   "tag": "credentials",
   "notice": "SD3.5-M is gated on Hugging Face, so you must authenticate with your own account and accept the model license before downloading."
  }
 ],
 "best": true,
 "score": 1.0,
 "evidence": [],
 "url": "https://dedupedai.com/use-cases/worldbench-diffusionopsd/post-train-sd35-on-image-reward/",
 "md": "https://dedupedai.com/use-cases/worldbench-diffusionopsd/post-train-sd35-on-image-reward/index.md",
 "disclaimer": "Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked \"Seen in the wild\", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email hello@dedupedai.com and we will look at it promptly.",
 "api": "https://dedupedai.com/api/v1/usecases/worldbench-diffusionopsd--post-train-sd35-on-image-reward.json",
 "api_version": "v1"
}