Diffusion fashions have not too long ago emerged because the de facto customary for producing complicated, high-dimensional outputs. Chances are you’ll know them for his or her capacity to supply gorgeous AI artwork and hyper-realistic artificial photographs, however they’ve additionally discovered success in different purposes corresponding to drug design and steady management. The important thing concept behind diffusion fashions is to iteratively remodel random noise right into a pattern, corresponding to a picture or protein construction. That is sometimes motivated as a most chance estimation drawback, the place the mannequin is skilled to generate samples that match the coaching knowledge as carefully as potential.
Nevertheless, most use instances of diffusion fashions usually are not straight involved with matching the coaching knowledge, however as a substitute with a downstream goal. We don’t simply need a picture that appears like current photographs, however one which has a particular sort of look; we don’t simply desire a drug molecule that’s bodily believable, however one that’s as efficient as potential. On this submit, we present how diffusion fashions may be skilled on these downstream goals straight utilizing reinforcement studying (RL). To do that, we finetune Steady Diffusion on quite a lot of goals, together with picture compressibility, human-perceived aesthetic high quality, and prompt-image alignment. The final of those goals 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 guage generated photographs.
Denoising Diffusion Coverage Optimization
When turning diffusion into an RL drawback, we make solely probably the most fundamental assumption: given a pattern (e.g. a picture), we’ve got entry to a reward operate that we will consider to inform us how “good” that pattern is. Our aim is for the diffusion mannequin to generate samples that maximize this reward operate.
Diffusion fashions are sometimes skilled utilizing a loss operate derived from most chance estimation (MLE), that means they’re inspired to generate samples that make the coaching knowledge look extra possible. Within the RL setting, we now not have coaching knowledge, solely samples from the diffusion mannequin and their related rewards. A method 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 offers us an algorithm that we name reward-weighted regression (RWR), after current algorithms from RL literature.
Nevertheless, there are just a few issues with this strategy. One is that RWR is just not a very precise algorithm — it maximizes the reward solely roughly (see Nair et. al., Appendix A). The MLE-inspired loss for diffusion can be not precise and is as a substitute 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 whole sequence of denoising steps that acquired us there. To do that, we reframe the diffusion course of as a multi-step Markov determination 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 simple to compute.
We selected to use coverage gradient algorithms resulting from their ease of implementation and previous success in language mannequin finetuning. This led to 2 variants of DDPO: DDPOSF, which makes use of the easy rating operate 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 Steady Diffusion Utilizing DDPO
For our fundamental outcomes, we finetune Steady Diffusion v1-4 utilizing DDPOIS. Now we have 4 duties, every outlined by a special reward operate:
- Compressibility: How simple is the picture to compress utilizing the JPEG algorithm? The reward is the damaging file dimension 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 optimistic file dimension 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 skilled 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 Steady Diffusion is a text-to-image mannequin, we additionally want to choose 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”, “enjoying chess”, and “using a motorcycle”. We discovered that Steady Diffusion typically struggled to supply 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 easy rewards (compressibility, incompressibility, and aesthetic high quality). The entire photographs are generated with the identical random seed. Within the high left quadrant, we illustrate what “vanilla” Steady Diffusion generates for 9 totally different animals; the entire RL-finetuned fashions present a transparent qualitative distinction. Curiously, the aesthetic high quality mannequin (high 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 complicated 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 Steady Diffusion. Curiously, the mannequin shifts in direction of a extra cartoon-like type, which was not intentional. We hypothesize that it’s because animals doing human-like actions usually tend to seem in a cartoon-like type within the pretraining knowledge, 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 massive language fashions with RL: for instance, fashions finetuned on instruction-following solely in English typically 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 an inventory of 45 frequent animals. We discover that it generalizes not solely to unseen animals but in addition to on a regular basis objects.
Our prompt-image alignment mannequin used the identical listing of 45 frequent animals throughout coaching, and solely three actions. We discover that it generalizes not solely to unseen animals but in addition to unseen actions, and even novel mixtures 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 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 a substitute producing textual content loosely resembling the proper 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 exhausting to beat in terms of producing complicated, high-dimensional outputs. Nevertheless, to this point they’ve principally been profitable in purposes the place the aim is to study patterns from heaps and plenty of knowledge (for instance, image-caption pairs). What we’ve discovered is a option to successfully practice 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 Steady Diffusion, are first skilled 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 not too long ago found out the way to produce highly effective chatbots utilizing reward capabilities based mostly on AI suggestions as a substitute. 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 as if 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 purposes corresponding to video era, music era, picture modifying, protein synthesis, robotics, and extra.
Moreover, the “pretrain + finetune” paradigm is just not the one approach to make use of DDPO. So long as you have got a very good 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 purposes of RL to the subsequent stage — and even to find new ones.
This submit is predicated on the next paper:
If you wish to study extra about DDPO, you possibly can try the paper, web site, authentic code, or get the mannequin weights on Hugging Face. If you wish to use DDPO in your personal challenge, try my PyTorch + LoRA implementation the place you possibly can finetune Steady 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}
}