optimum-intel-internal-testing/tiny-random-ltx2
098k
1{2 "_class_name": "AutoencoderKLLTX2Video",3 "_diffusers_version": "0.38.0",4 "block_out_channels": [5 8,6 8,7 8,8 89 ],10 "decoder_block_out_channels": [11 8,12 16,13 3214 ],15 "decoder_causal": false,16 "decoder_inject_noise": [17 false,18 false,19 false,20 false21 ],22 "decoder_layers_per_block": [23 1,24 1,25 1,26 127 ],28 "decoder_spatial_padding_mode": "zeros",29 "decoder_spatio_temporal_scaling": [30 true,31 true,32 true33 ],34 "down_block_types": [35 "LTX2VideoDownBlock3D",36 "LTX2VideoDownBlock3D",37 "LTX2VideoDownBlock3D",38 "LTX2VideoDownBlock3D"39 ],40 "downsample_type": [41 "spatial",42 "temporal",43 "spatiotemporal",44 "spatiotemporal"45 ],46 "encoder_causal": true,47 "encoder_spatial_padding_mode": "zeros",48 "in_channels": 3,49 "latent_channels": 8,50 "layers_per_block": [51 1,52 1,53 1,54 1,55 156 ],57 "out_channels": 3,58 "patch_size": 4,59 "patch_size_t": 1,60 "resnet_norm_eps": 1e-06,61 "scaling_factor": 1.0,62 "spatial_compression_ratio": 32,63 "spatio_temporal_scaling": [64 true,65 true,66 true,67 true68 ],69 "temporal_compression_ratio": 8,70 "timestep_conditioning": false,71 "upsample_factor": [72 2,73 2,74 275 ],76 "upsample_residual": [77 true,78 true,79 true80 ],81 "latents_mean_data": [82 0.0,83 0.0,84 0.0,85 0.0,86 0.0,87 0.0,88 0.0,89 0.090 ],91 "latents_std_data": [92 1.0,93 1.0,94 1.0,95 1.0,96 1.0,97 1.0,98 1.0,99 1.0100 ],101 "audio_latents_mean_data": [102 0.0,103 0.0,104 0.0,105 0.0,106 0.0,107 0.0,108 0.0,109 0.0,110 0.0,111 0.0,112 0.0,113 0.0,114 0.0,115 0.0,116 0.0,117 0.0,118 0.0,119 0.0,120 0.0,121 0.0,122 0.0,123 0.0,124 0.0,125 0.0,126 0.0,127 0.0,128 0.0,129 0.0,130 0.0,131 0.0,132 0.0,133 0.0,134 0.0,135 0.0,136 0.0,137 0.0,138 0.0,139 0.0,140 0.0,141 0.0,142 0.0,143 0.0,144 0.0,145 0.0,146 0.0,147 0.0,148 0.0,149 0.0,150 0.0,151 0.0,152 0.0,153 0.0,154 0.0,155 0.0,156 0.0,157 0.0,158 0.0,159 0.0,160 0.0,161 0.0,162 0.0,163 0.0,164 0.0,165 0.0,166 0.0,167 0.0,168 0.0,169 0.0,170 0.0,171 0.0,172 0.0,173 0.0,174 0.0,175 0.0,176 0.0,177 0.0,178 0.0,179 0.0,180 0.0,181 0.0,182 0.0,183 0.0,184 0.0,185 0.0,186 0.0,187 0.0,188 0.0,189 0.0,190 0.0,191 0.0,192 0.0,193 0.0,194 0.0,195 0.0,196 0.0,197 0.0,198 0.0,199 0.0,200 0.0,201 0.0,202 0.0,203 0.0,204 0.0,205 0.0,206 0.0,207 0.0,208 0.0,209 0.0,210 0.0,211 0.0,212 0.0,213 0.0,214 0.0,215 0.0,216 0.0,217 0.0,218 0.0,219 0.0,220 0.0,221 0.0,222 0.0,223 0.0,224 0.0,225 0.0,226 0.0,227 0.0,228 0.0,229 0.0230 ],231 "audio_latents_std_data": [232 1.0,233 1.0,234 1.0,235 1.0,236 1.0,237 1.0,238 1.0,239 1.0,240 1.0,241 1.0,242 1.0,243 1.0,244 1.0,245 1.0,246 1.0,247 1.0,248 1.0,249 1.0,250 1.0,251 1.0,252 1.0,253 1.0,254 1.0,255 1.0,256 1.0,257 1.0,258 1.0,259 1.0,260 1.0,261 1.0,262 1.0,263 1.0,264 1.0,265 1.0,266 1.0,267 1.0,268 1.0,269 1.0,270 1.0,271 1.0,272 1.0,273 1.0,274 1.0,275 1.0,276 1.0,277 1.0,278 1.0,279 1.0,280 1.0,281 1.0,282 1.0,283 1.0,284 1.0,285 1.0,286 1.0,287 1.0,288 1.0,289 1.0,290 1.0,291 1.0,292 1.0,293 1.0,294 1.0,295 1.0,296 1.0,297 1.0,298 1.0,299 1.0,300 1.0,301 1.0,302 1.0,303 1.0,304 1.0,305 1.0,306 1.0,307 1.0,308 1.0,309 1.0,310 1.0,311 1.0,312 1.0,313 1.0,314 1.0,315 1.0,316 1.0,317 1.0,318 1.0,319 1.0,320 1.0,321 1.0,322 1.0,323 1.0,324 1.0,325 1.0,326 1.0,327 1.0,328 1.0,329 1.0,330 1.0,331 1.0,332 1.0,333 1.0,334 1.0,335 1.0,336 1.0,337 1.0,338 1.0,339 1.0,340 1.0,341 1.0,342 1.0,343 1.0,344 1.0,345 1.0,346 1.0,347 1.0,348 1.0,349 1.0,350 1.0,351 1.0,352 1.0,353 1.0,354 1.0,355 1.0,356 1.0,357 1.0,358 1.0,359 1.0360 ]361}