Diffusion fashions have lately emerged because the de facto customary for producing advanced, high-dimensional outputs. You could know them for his or her capacity to provide gorgeous AI artwork and hyper-realistic artificial photographs, however they’ve additionally discovered success in different purposes similar to drug design and steady management. The important thing concept behind diffusion fashions is to iteratively rework random noise right into a pattern, similar to a picture or protein construction. That is sometimes motivated as a most probability estimation drawback, the place the mannequin is educated to generate samples that match the coaching information as carefully as attainable.
Nevertheless, most use circumstances of diffusion fashions will not be straight involved with matching the coaching information, however as an alternative with a downstream goal. We don’t simply need a picture that appears like present photographs, however one which has a selected sort of look; we don’t simply need a drug molecule that’s bodily believable, however one that’s as efficient as attainable. On this publish, we present how diffusion fashions may be educated on these downstream aims straight utilizing reinforcement studying (RL). To do that, we finetune Secure Diffusion on quite a lot of aims, together with picture compressibility, human-perceived aesthetic high quality, and prompt-image alignment. The final of those aims makes use of suggestions from a big vision-language mannequin to enhance the mannequin’s efficiency on uncommon prompts, demonstrating how highly effective AI fashions can be utilized to enhance one another with none people within the loop.
A diagram illustrating the prompt-image alignment goal. It makes use of LLaVA, a big vision-language mannequin, to judge generated photographs.
Denoising Diffusion Coverage Optimization
When turning diffusion into an RL drawback, we make solely essentially the most primary assumption: given a pattern (e.g. a picture), we now have entry to a reward perform that we are able to consider to inform us how “good” that pattern is. Our aim is for the diffusion mannequin to generate samples that maximize this reward perform.
Diffusion fashions are sometimes educated utilizing a loss perform derived from most probability estimation (MLE), which means they’re inspired to generate samples that make the coaching information look extra possible. Within the RL setting, we not have coaching information, solely samples from the diffusion mannequin and their related rewards. A technique we are able to nonetheless use the identical MLE-motivated loss perform is by treating the samples as coaching information and incorporating the rewards by weighting the loss for every pattern by its reward. This offers us an algorithm that we name reward-weighted regression (RWR), after present algorithms from RL literature.
Nevertheless, there are a number of issues with this strategy. One is that RWR is just not a very actual algorithm — it maximizes the reward solely roughly (see Nair et. al., Appendix A). The MLE-inspired loss for diffusion can also be not actual and is as an alternative derived utilizing a variational sure on the true probability of every pattern. Which means that RWR maximizes the reward by two ranges of approximation, which we discover considerably hurts its efficiency.
We consider two variants of DDPO and two variants of RWR on three reward features and discover that DDPO persistently achieves one of the best efficiency.
The important thing perception of our algorithm, which we name denoising diffusion coverage optimization (DDPO), is that we are able to higher maximize the reward of the ultimate pattern if we take note of your entire sequence of denoising steps that bought us there. To do that, we reframe the diffusion course of as a multi-step Markov resolution course of (MDP). In MDP terminology: every denoising step is an motion, and the agent solely will get a reward on the ultimate step of every denoising trajectory when the ultimate pattern is produced. This framework permits us to use many highly effective algorithms from RL literature which can be designed particularly for multi-step MDPs. As an alternative of utilizing the approximate probability of the ultimate pattern, these algorithms use the precise probability of every denoising step, which is extraordinarily straightforward to compute.
We selected to use coverage gradient algorithms attributable to their ease of implementation and previous success in language mannequin finetuning. This led to 2 variants of DDPO: DDPOSF, which makes use of the straightforward rating perform estimator of the coverage gradient also referred to as REINFORCE; and DDPOIS, which makes use of a extra highly effective significance sampled estimator. DDPOIS is our best-performing algorithm and its implementation carefully follows that of proximal coverage optimization (PPO).
Finetuning Secure Diffusion Utilizing DDPO
For our most important outcomes, we finetune Secure Diffusion v1-4 utilizing DDPOIS. We have now 4 duties, every outlined by a unique reward perform:
- Compressibility: How straightforward is the picture to compress utilizing the JPEG algorithm? The reward is the detrimental file measurement of the picture (in kB) when saved as a JPEG.
- Incompressibility: How exhausting is the picture to compress utilizing the JPEG algorithm? The reward is the constructive file measurement of the picture (in kB) when saved as a JPEG.
- Aesthetic High quality: How aesthetically interesting is the picture to the human eye? The reward is the output of the LAION aesthetic predictor, which is a neural community educated on human preferences.
- Immediate-Picture Alignment: How effectively does the picture signify what was requested for within the immediate? This one is a little more difficult: we feed the picture into LLaVA, ask it to explain the picture, after which compute the similarity between that description and the unique immediate utilizing BERTScore.
Since Secure Diffusion is a text-to-image mannequin, we additionally want to select a set of prompts to present it throughout finetuning. For the primary three duties, we use easy prompts of the shape “a(n) [animal]”. For prompt-image alignment, we use prompts of the shape “a(n) [animal] [activity]”, the place the actions are “washing dishes”, “taking part in chess”, and “using a motorbike”. We discovered that Secure Diffusion usually struggled to provide photographs that matched the immediate for these uncommon eventualities, leaving loads of room for enchancment with RL finetuning.
First, we illustrate the efficiency of DDPO on the straightforward rewards (compressibility, incompressibility, and aesthetic high quality). The entire photographs are generated with the identical random seed. Within the prime left quadrant, we illustrate what “vanilla” Secure Diffusion generates for 9 completely different animals; all the RL-finetuned fashions present a transparent qualitative distinction. Curiously, the aesthetic high quality mannequin (prime proper) tends in direction of minimalist black-and-white line drawings, revealing the sorts of photographs that the LAION aesthetic predictor considers “extra aesthetic”.
Subsequent, we reveal DDPO on the extra advanced prompt-image alignment activity. Right here, we present a number of snapshots from the coaching course of: every collection of three photographs exhibits samples for a similar immediate and random seed over time, with the primary pattern coming from vanilla Secure Diffusion. Curiously, the mannequin shifts in direction of a extra cartoon-like type, which was not intentional. We hypothesize that it is because animals doing human-like actions usually tend to seem in a cartoon-like type within the pretraining information, so the mannequin shifts in direction of this type to extra simply align with the immediate by leveraging what it already is aware of.
Surprising Generalization
Shocking generalization has been discovered to come up when finetuning giant language fashions with RL: for instance, fashions finetuned on instruction-following solely in English usually enhance in different languages. We discover that the identical phenomenon happens with text-to-image diffusion fashions. For instance, our aesthetic high quality mannequin was finetuned utilizing prompts that have been chosen from a listing of 45 frequent animals. We discover that it generalizes not solely to unseen animals but additionally to on a regular basis objects.
Our prompt-image alignment mannequin used the identical record of 45 frequent animals throughout coaching, and solely three actions. We discover that it generalizes not solely to unseen animals but additionally to unseen actions, and even novel combos of the 2.
Overoptimization
It’s well-known that finetuning on a reward perform, particularly a discovered one, can result in reward overoptimization the place the mannequin exploits the reward perform to realize a excessive reward in a non-useful method. Our setting isn’t any exception: in all of the duties, the mannequin ultimately destroys any significant picture content material to maximise reward.
We additionally found that LLaVA is prone to typographic assaults: when optimizing for alignment with respect to prompts of the shape “[n] animals”, DDPO was in a position to efficiently idiot LLaVA by as an alternative producing textual content loosely resembling the right quantity.
There may be presently no general-purpose methodology for stopping overoptimization, and we spotlight this drawback as an vital space for future work.
Conclusion
Diffusion fashions are exhausting to beat relating to producing advanced, high-dimensional outputs. Nevertheless, up to now they’ve largely been profitable in purposes the place the aim is to study patterns from heaps and plenty of information (for instance, image-caption pairs). What we’ve discovered is a technique to successfully prepare diffusion fashions in a method that goes past pattern-matching — and with out essentially requiring any coaching information. The probabilities are restricted solely by the standard and creativity of your reward perform.
The best way we used DDPO on this work is impressed by the current successes of language mannequin finetuning. OpenAI’s GPT fashions, like Secure Diffusion, are first educated on big quantities of Web information; they’re then finetuned with RL to provide helpful instruments like ChatGPT. Usually, their reward perform is discovered from human preferences, however others have extra lately found out methods to produce highly effective chatbots utilizing reward features based mostly on AI suggestions as an alternative. In comparison with the chatbot regime, our experiments are small-scale and restricted in scope. However contemplating the big success of this “pretrain + finetune” paradigm in language modeling, it actually looks like it’s price pursuing additional on this planet of diffusion fashions. We hope that others can construct on our work to enhance giant diffusion fashions, not only for text-to-image era, however for a lot of thrilling purposes similar to video era, music era, picture modifying, protein synthesis, robotics, and extra.
Moreover, the “pretrain + finetune” paradigm is just not the one method to make use of DDPO. So long as you’ve got a very good reward perform, there’s nothing stopping you from coaching with RL from the beginning. Whereas this setting is as-yet unexplored, it is a place the place the strengths of DDPO may actually shine. Pure RL has lengthy been utilized to all kinds of domains starting from taking part in video games to robotic manipulation to nuclear fusion to chip design. Including the highly effective expressivity of diffusion fashions to the combo has the potential to take present purposes of RL to the following stage — and even to find new ones.
This publish is predicated on the next paper:
If you wish to study extra about DDPO, you may take a look at the paper, web site, unique code, or get the mannequin weights on Hugging Face. If you wish to use DDPO in your personal venture, take a look at my PyTorch + LoRA implementation the place you may finetune Secure Diffusion with lower than 10GB of GPU reminiscence!
If DDPO conjures up your work, please cite it with:
@misc{black2023ddpo,
title={Coaching Diffusion Fashions with Reinforcement Studying},
creator={Kevin Black and Michael Janner and Yilun Du and Ilya Kostrikov and Sergey Levine},
12 months={2023},
eprint={2305.13301},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
