aMUSEd¶
aMUSEd was introduced in aMUSEd: An Open MUSE Reproduction by Suraj Patil, William Berman, Robin Rombach, and Patrick von Platen.
Amused is a lightweight text to image model based off of the MUSE architecture. Amused is particularly useful in applications that require a lightweight and fast model such as generating many images quickly at once.
Amused is a vqvae token based transformer that can generate an image in fewer forward passes than many diffusion models. In contrast with muse, it uses the smaller text encoder CLIP-L/14 instead of t5-xxl. Due to its small parameter count and few forward pass generation process, amused can generate many images quickly. This benefit is seen particularly at larger batch sizes.
The abstract from the paper is:
We present aMUSEd, an open-source, lightweight masked image model (MIM) for text-to-image generation based on MUSE. With 10 percent of MUSE's parameters, aMUSEd is focused on fast image generation. We believe MIM is under-explored compared to latent diffusion, the prevailing approach for text-to-image generation. Compared to latent diffusion, MIM requires fewer inference steps and is more interpretable. Additionally, MIM can be fine-tuned to learn additional styles with only a single image. We hope to encourage further exploration of MIM by demonstrating its effectiveness on large-scale text-to-image generation and releasing reproducible training code. We also release checkpoints for two models which directly produce images at 256x256 and 512x512 resolutions.
Model | Params |
---|---|
amused-256 | 603M |
amused-512 | 608M |
AmusedPipeline¶
mindone.diffusers.AmusedPipeline
¶
Bases: DiffusionPipeline
Source code in mindone/diffusers/pipelines/amused/pipeline_amused.py
46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 |
|
mindone.diffusers.AmusedPipeline.__call__(prompt=None, height=None, width=None, num_inference_steps=12, guidance_scale=10.0, negative_prompt=None, num_images_per_prompt=1, generator=None, latents=None, prompt_embeds=None, encoder_hidden_states=None, negative_prompt_embeds=None, negative_encoder_hidden_states=None, output_type='pil', return_dict=False, callback=None, callback_steps=1, cross_attention_kwargs=None, micro_conditioning_aesthetic_score=6, micro_conditioning_crop_coord=(0, 0), temperature=(2, 0))
¶
The call function to the pipeline for generation.
PARAMETER | DESCRIPTION |
---|---|
prompt |
The prompt or prompts to guide image generation. If not defined, you need to pass
TYPE:
|
height |
The height in pixels of the generated image.
TYPE:
|
width |
The width in pixels of the generated image.
TYPE:
|
num_inference_steps |
The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
TYPE:
|
guidance_scale |
A higher guidance scale value encourages the model to generate images closely linked to the text
TYPE:
|
negative_prompt |
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass
TYPE:
|
num_images_per_prompt |
The number of images to generate per prompt.
TYPE:
|
generator |
A
TYPE:
|
latents |
Pre-generated tokens representing latent vectors in
TYPE:
|
prompt_embeds |
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the
TYPE:
|
encoder_hidden_states |
Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.
TYPE:
|
negative_prompt_embeds |
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided,
TYPE:
|
negative_encoder_hidden_states |
Analogous to
TYPE:
|
output_type |
The output format of the generated image. Choose between
TYPE:
|
return_dict |
Whether or not to return a [
TYPE:
|
callback |
A function that calls every
TYPE:
|
callback_steps |
The frequency at which the
TYPE:
|
cross_attention_kwargs |
A kwargs dictionary that if specified is passed along to the [
TYPE:
|
micro_conditioning_aesthetic_score |
The targeted aesthetic score according to the laion aesthetic classifier. See https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of https://arxiv.org/abs/2307.01952.
TYPE:
|
micro_conditioning_crop_coord |
The targeted height, width crop coordinates. See the micro-conditioning section of https://arxiv.org/abs/2307.01952.
TYPE:
|
temperature |
Configures the temperature scheduler on
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
[ |
Source code in mindone/diffusers/pipelines/amused/pipeline_amused.py
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 |
|
mindone.diffusers.AmusedImg2ImgPipeline
¶
Bases: DiffusionPipeline
Source code in mindone/diffusers/pipelines/amused/pipeline_amused_img2img.py
56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 |
|
mindone.diffusers.AmusedImg2ImgPipeline.__call__(prompt=None, image=None, strength=0.5, num_inference_steps=12, guidance_scale=10.0, negative_prompt=None, num_images_per_prompt=1, generator=None, prompt_embeds=None, encoder_hidden_states=None, negative_prompt_embeds=None, negative_encoder_hidden_states=None, output_type='pil', return_dict=False, callback=None, callback_steps=1, cross_attention_kwargs=None, micro_conditioning_aesthetic_score=6, micro_conditioning_crop_coord=(0, 0), temperature=(2, 0))
¶
The call function to the pipeline for generation.
PARAMETER | DESCRIPTION |
---|---|
prompt |
The prompt or prompts to guide image generation. If not defined, you need to pass
TYPE:
|
image |
TYPE:
|
strength |
Indicates extent to transform the reference
TYPE:
|
num_inference_steps |
The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
TYPE:
|
guidance_scale |
A higher guidance scale value encourages the model to generate images closely linked to the text
TYPE:
|
negative_prompt |
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass
TYPE:
|
num_images_per_prompt |
The number of images to generate per prompt.
TYPE:
|
generator |
A
TYPE:
|
prompt_embeds |
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the
TYPE:
|
encoder_hidden_states |
Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.
TYPE:
|
negative_prompt_embeds |
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided,
TYPE:
|
negative_encoder_hidden_states |
Analogous to
TYPE:
|
output_type |
The output format of the generated image. Choose between
TYPE:
|
return_dict |
Whether or not to return a [
TYPE:
|
callback |
A function that calls every
TYPE:
|
callback_steps |
The frequency at which the
TYPE:
|
cross_attention_kwargs |
A kwargs dictionary that if specified is passed along to the [
TYPE:
|
micro_conditioning_aesthetic_score |
The targeted aesthetic score according to the laion aesthetic classifier. See https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of https://arxiv.org/abs/2307.01952.
TYPE:
|
micro_conditioning_crop_coord |
The targeted height, width crop coordinates. See the micro-conditioning section of https://arxiv.org/abs/2307.01952.
TYPE:
|
temperature |
Configures the temperature scheduler on
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
[ |
Source code in mindone/diffusers/pipelines/amused/pipeline_amused_img2img.py
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 |
|
mindone.diffusers.AmusedInpaintPipeline
¶
Bases: DiffusionPipeline
Source code in mindone/diffusers/pipelines/amused/pipeline_amused_inpaint.py
64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 |
|
mindone.diffusers.AmusedInpaintPipeline.__call__(prompt=None, image=None, mask_image=None, strength=1.0, num_inference_steps=12, guidance_scale=10.0, negative_prompt=None, num_images_per_prompt=1, generator=None, prompt_embeds=None, encoder_hidden_states=None, negative_prompt_embeds=None, negative_encoder_hidden_states=None, output_type='pil', return_dict=True, callback=None, callback_steps=1, cross_attention_kwargs=None, micro_conditioning_aesthetic_score=6, micro_conditioning_crop_coord=(0, 0), temperature=(2, 0))
¶
The call function to the pipeline for generation.
PARAMETER | DESCRIPTION |
---|---|
prompt |
The prompt or prompts to guide image generation. If not defined, you need to pass
TYPE:
|
image |
TYPE:
|
mask_image |
TYPE:
|
strength |
Indicates extent to transform the reference
TYPE:
|
num_inference_steps |
The number of denoising steps. More denoising steps usually lead to a higher quality image at the expense of slower inference.
TYPE:
|
guidance_scale |
A higher guidance scale value encourages the model to generate images closely linked to the text
TYPE:
|
negative_prompt |
The prompt or prompts to guide what to not include in image generation. If not defined, you need to
pass
TYPE:
|
num_images_per_prompt |
The number of images to generate per prompt.
TYPE:
|
generator |
A
TYPE:
|
prompt_embeds |
Pre-generated text embeddings. Can be used to easily tweak text inputs (prompt weighting). If not
provided, text embeddings are generated from the
TYPE:
|
encoder_hidden_states |
Pre-generated penultimate hidden states from the text encoder providing additional text conditioning.
TYPE:
|
negative_prompt_embeds |
Pre-generated negative text embeddings. Can be used to easily tweak text inputs (prompt weighting). If
not provided,
TYPE:
|
negative_encoder_hidden_states |
Analogous to
TYPE:
|
output_type |
The output format of the generated image. Choose between
TYPE:
|
return_dict |
Whether or not to return a [
TYPE:
|
callback |
A function that calls every
TYPE:
|
callback_steps |
The frequency at which the
TYPE:
|
cross_attention_kwargs |
A kwargs dictionary that if specified is passed along to the [
TYPE:
|
micro_conditioning_aesthetic_score |
The targeted aesthetic score according to the laion aesthetic classifier. See https://laion.ai/blog/laion-aesthetics/ and the micro-conditioning section of https://arxiv.org/abs/2307.01952.
TYPE:
|
micro_conditioning_crop_coord |
The targeted height, width crop coordinates. See the micro-conditioning section of https://arxiv.org/abs/2307.01952.
TYPE:
|
temperature |
Configures the temperature scheduler on
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
[ |
Source code in mindone/diffusers/pipelines/amused/pipeline_amused_inpaint.py
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 |
|