docs: update README.md

README.md

@@ -563,7 +563,7 @@ As of 2024, if we want to achieve a region guided diffusion system, some possibl
 2. attention decomposition: lets say attention is like `y=softmax(q@k)@v`, then one can achieve attention decomposition like `y=mask_A * softmax(q@k_A)@v_A + mask_B * softmax(q@k_B)@v_B` where mask_A, k_A, v_A are masks, k, v for region A; mask_B, k_B, v_B are masks, k, v for region B. This method usually yields image quality a bit better than (1) and some people call it Attention Couple or Region Prompter Attention Mode. But this method has a consideration: the mask only makes regional attention numerically possible, but it does not force the UNet to really attend its activations in those regions. That is to say, the attention is indeed masked, but there is no promise that the attention softmax will really be activated in the masked area, and there is also no promise that the attention softmax will never be activated outside the masked area.
 3. attention score manipulation: this is a more advanced method compared to (2). It directly manipulates the attention scores to make sure that the activations in mask each area are encouraged and those outside the masks are discouraged. The formulation is like `y=softmax(modify(q@k))@v` where `modify()` is a complicated non-linear function with many normalizations and tricks to change the score's distributions. This method goes beyond a simple masked attention to really make sure that those layers get wanted activations. A typical example is [Dense Diffusion](https://github.com/naver-ai/DenseDiffusion).
 4. gradient optimization: since the attention can tell us where each part is corresponding to what prompts, we can split prompts into segments and then get attention activations to each prompt segment. Then we compare those activations with external masks to compute a loss function, and back propagate the gradients. Those methods are usually very high quality but VRAM hungry and very slow. Typical methods are [BoxDiff](https://github.com/showlab/BoxDiff) and [Attend-and-Excite](https://github.com/yuval-alaluf/Attend-and-Excite).
-5. Use external control models like gligen and [InstanceDiffusion](https://github.com/frank-xwang/InstanceDiffusion). Those methods give the highest benchmark performance on region following but will also introduce some style offset to the base model since they are trained parameters. Also, those methods need to convert prompts to vectors and usually do not support prompts of arbitary length (but one can use them together with other attention methods to achieve arbitrary length).
+5. Use external control models like gligen and [InstanceDiffusion](https://github.com/frank-xwang/InstanceDiffusion). Those methods give the highest benchmark performance on region following but will also introduce some style offset to the base model since they are trained parameters. Also, those methods need to convert prompts to vectors and usually do not support prompts of arbitrary length (but one can use them together with other attention methods to achieve arbitrary length).
 6. Some more possible layer options like layerdiffuse and [mulan](https://mulan-dataset.github.io/).
 
 In this repo I wrote a baseline formulation based on (3). I consider this parameter-free formulation as a very standard baseline implementation that will almost introduce zero style offsets or quality degradation. In the future we may consider training some parametrized methods for Omost.