Diffusion fashions have lately emerged because the de facto commonplace for producing advanced, high-dimensional outputs. You might know them for his or her skill to supply beautiful AI artwork and hyper-realistic artificial photographs, however they’ve additionally discovered success in different functions reminiscent of drug design and steady management. The important thing thought behind diffusion fashions is to iteratively remodel random noise right into a pattern, reminiscent of a picture or protein construction. That is usually motivated as a most chance estimation drawback, the place the mannequin is educated to generate samples that match the coaching knowledge as intently as attainable.
Nonetheless, most use instances of diffusion fashions usually are not straight involved with matching the coaching knowledge, however as an alternative with a downstream goal. We don’t simply need a picture that appears like current photographs, however one which has a selected kind of look; we don’t simply desire a drug molecule that’s bodily believable, however one that’s as efficient as attainable. On this put up, 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 a wide range 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 fundamental assumption: given a pattern (e.g. a picture), we now have entry to a reward operate that we will consider to inform us how “good” that pattern is. Our objective is for the diffusion mannequin to generate samples that maximize this reward operate.
Diffusion fashions are usually educated utilizing a loss operate derived from most chance estimation (MLE), which means they’re inspired to generate samples that make the coaching knowledge look extra possible. Within the RL setting, we not have coaching knowledge, solely samples from the diffusion mannequin and their related rewards. A technique we will nonetheless use the identical MLE-motivated loss operate is by treating the samples as coaching knowledge and incorporating the rewards by weighting the loss for every pattern by its reward. This provides us an algorithm that we name reward-weighted regression (RWR), after current algorithms from RL literature.
Nonetheless, there are a couple of issues with this method. One is that RWR will not be 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 chance of every pattern. Which means that RWR maximizes the reward by way of 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 capabilities and discover that DDPO constantly achieves the very best efficiency.
The important thing perception of our algorithm, which we name denoising diffusion coverage optimization (DDPO), is that we will higher maximize the reward of the ultimate pattern if we take note of the complete sequence of denoising steps that obtained 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 might be designed particularly for multi-step MDPs. As a substitute of utilizing the approximate chance of the ultimate pattern, these algorithms use the precise chance 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 operate estimator of the coverage gradient often known as REINFORCE; and DDPOIS, which makes use of a extra highly effective significance sampled estimator. DDPOIS is our best-performing algorithm and its implementation intently follows that of proximal coverage optimization (PPO).
Finetuning Secure Diffusion Utilizing DDPO
For our foremost outcomes, we finetune Secure Diffusion v1-4 utilizing DDPOIS. Now we have 4 duties, every outlined by a unique reward operate:
- Compressibility: How straightforward is the picture to compress utilizing the JPEG algorithm? The reward is the unfavorable file measurement of the picture (in kB) when saved as a JPEG.
- Incompressibility: How laborious 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 properly does the picture characterize what was requested for within the immediate? This one is a little more sophisticated: 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 choose a set of prompts to offer 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”, “enjoying chess”, and “using a motorcycle”. We discovered that Secure Diffusion usually struggled to supply photographs that matched the immediate for these uncommon situations, 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). All the photographs are generated with the identical random seed. Within the prime left quadrant, we illustrate what “vanilla” Secure Diffusion generates for 9 totally different animals; all the RL-finetuned fashions present a transparent qualitative distinction. Apparently, the aesthetic high quality mannequin (prime proper) tends in the direction of minimalist black-and-white line drawings, revealing the sorts of photographs that the LAION aesthetic predictor considers “extra aesthetic”.
Subsequent, we display DDPO on the extra advanced prompt-image alignment activity. Right here, we present a number of snapshots from the coaching course of: every sequence of three photographs reveals samples for a similar immediate and random seed over time, with the primary pattern coming from vanilla Secure Diffusion. Apparently, the mannequin shifts in the direction of a extra cartoon-like fashion, which was not intentional. We hypothesize that it is because animals doing human-like actions usually tend to seem in a cartoon-like fashion within the pretraining knowledge, so the mannequin shifts in the direction of this fashion to extra simply align with the immediate by leveraging what it already is aware of.
Surprising Generalization
Stunning generalization has been discovered to come up when finetuning massive 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 had been chosen from a listing of 45 widespread 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 widespread 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 operate, particularly a discovered one, can result in reward overoptimization the place the mannequin exploits the reward operate to attain a excessive reward in a non-useful approach. Our setting is not any exception: in all of the duties, the mannequin finally destroys any significant picture content material to maximise reward.
We additionally found that LLaVA is inclined to typographic assaults: when optimizing for alignment with respect to prompts of the shape “[n] animals”, DDPO was capable of efficiently idiot LLaVA by as an alternative producing textual content loosely resembling the right quantity.
There’s presently no general-purpose methodology for stopping overoptimization, and we spotlight this drawback as an vital space for future work.
Conclusion
Diffusion fashions are laborious to beat with regards to producing advanced, high-dimensional outputs. Nonetheless, up to now they’ve principally been profitable in functions the place the objective is to study patterns from heaps and plenty of knowledge (for instance, image-caption pairs). What we’ve discovered is a method to successfully prepare diffusion fashions in a approach that goes past pattern-matching — and with out essentially requiring any coaching knowledge. The probabilities are restricted solely by the standard and creativity of your reward operate.
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 knowledge; they’re then finetuned with RL to supply helpful instruments like ChatGPT. Usually, their reward operate is discovered from human preferences, however others have extra lately found out tips on how to produce highly effective chatbots utilizing reward capabilities 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 definitely looks like it’s price pursuing additional on the planet of diffusion fashions. We hope that others can construct on our work to enhance massive diffusion fashions, not only for text-to-image era, however for a lot of thrilling functions reminiscent of video era, music era, picture enhancing, protein synthesis, robotics, and extra.
Moreover, the “pretrain + finetune” paradigm will not be the one approach to make use of DDPO. So long as you’ve reward operate, there’s nothing stopping you from coaching with RL from the beginning. Whereas this setting is as-yet unexplored, this can be a place the place the strengths of DDPO might actually shine. Pure RL has lengthy been utilized to all kinds of domains starting from enjoying 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 current functions of RL to the following degree — and even to find new ones.
This put up relies 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},
writer={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}
}