Spaces:
Runtime error
Runtime error
File size: 7,764 Bytes
9e188c8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"#| default_exp app"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"import gradio as gr\n",
"import cf_guidance\n",
"import min_diffusion\n",
"import torch\n",
"import nbdev"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"#| export\n",
"\n",
"## MODEL SETUP\n",
"######################################\n",
"######################################\n",
"model_name = 'stabilityai/stable-diffusion-2'\n",
"revision = 'fp16'\n",
"dtype = torch.float16\n",
"device = ('cpu','cuda')[torch.cuda.is_available()]\n",
"\n",
"# model parameters\n",
"better_vae = ''\n",
"unet_attn_slice = True\n",
"sampler_kls = 'dpm_multi'\n",
"hf_sampler = 'dpm_multi'\n",
"\n",
"model_kwargs = {\n",
" 'better_vae': better_vae,\n",
" 'unet_attn_slice': unet_attn_slice,\n",
" 'sampler_kls': hf_sampler,\n",
"}\n",
"\n",
"def load_model():\n",
" pipeline = min_diffusion.core.MinimalDiffusion(\n",
" model_name,\n",
" device,\n",
" dtype,\n",
" revision,\n",
" **model_kwargs,\n",
" )\n",
" pipeline.load()\n",
" return pipeline\n",
"######################################\n",
"######################################"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| export \n",
"\n",
"## GENERATION PARAMETERS\n",
"######################################\n",
"######################################\n",
"num_steps = 18\n",
"height, width = 768, 768\n",
"k_sampler = 'k_dpmpp_2m' #'k_dpmpp_sde'\n",
"use_karras_sigmas = True\n",
"\n",
"# a good negative prompt\n",
"NEG_PROMPT = \"ugly, stock photo, tiling, poorly drawn hands, poorly drawn feet, poorly drawn face, out of frame, mutation, mutated, extra limbs, extra legs, extra arms, disfigured, deformed, cross-eye, body out of frame, blurry, bad art, bad anatomy, blurred, text, watermark, grainy\"\n",
"\n",
"generation_kwargs = {\n",
" 'num_steps': num_steps,\n",
" 'height': height,\n",
" 'width': width,\n",
" 'k_sampler': k_sampler,\n",
" 'negative_prompt': NEG_PROMPT,\n",
" 'use_karras_sigmas': use_karras_sigmas,\n",
"}\n",
"######################################\n",
"######################################"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| export \n",
"\n",
"## dynamicCFG SETUP\n",
"######################################\n",
"######################################\n",
"\n",
"# default cosine schedule parameters\n",
"baseline_g = 9 # default, static guidance value\n",
"max_val = 9 # the max scheduled guidance scaling value\n",
"min_val = 6 # the minimum scheduled guidance value\n",
"num_warmup_steps = 0 # number of warmup steps\n",
"warmup_init_val = 0 # the intial warmup value\n",
"num_cycles = 0.5 # number of cosine cycles\n",
"k_decay = 1 # k-decay for cosine curve scaling \n",
"\n",
"# group the default schedule parameters\n",
"DEFAULT_COS_PARAMS = {\n",
" 'max_val': max_val,\n",
" 'num_steps': num_steps,\n",
" 'min_val': min_val,\n",
" 'num_cycles': num_cycles,\n",
" 'k_decay': k_decay,\n",
" 'num_warmup_steps': num_warmup_steps,\n",
" 'warmup_init_val': warmup_init_val,\n",
"}\n",
"\n",
"def cos_harness(new_params: dict) -> dict:\n",
" '''Creates cosine schedules with updated parameters in `new_params`\n",
" '''\n",
" # start from the given baseline `default_params`\n",
" cos_params = dict(DEFAULT_COS_PARAMS)\n",
" # update the with the new, given parameters\n",
" cos_params.update(new_params)\n",
" \n",
" # return the new cosine schedule\n",
" sched = cf_guidance.schedules.get_cos_sched(**cos_params)\n",
" return sched\n",
"\n",
"\n",
"# build the static schedule\n",
"static_sched = [baseline_g] * num_steps\n",
"\n",
"# build the inverted kdecay schedule\n",
"k_sched = cos_harness({'k_decay': 0.2})\n",
"inv_k_sched = [max_val - g + min_val for g in k_sched]\n",
"\n",
"# group the schedules \n",
"schedules = {\n",
" 'cosine': {'g': inv_k_sched},\n",
" 'static': {'g': static_sched},\n",
"}\n",
"######################################\n",
"######################################"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#| export \n",
"\n",
"def compare_dynamic_guidance(prompt):\n",
" '''\n",
" Compares the default, static Classifier-free Guidance to a dynamic schedule. \n",
"\n",
" Model and sampling paramters:\n",
" Stable Diffusion 2 v-model\n",
" Half-precision\n",
" DPM++ 2M sampler, with Karras sigma schedule\n",
" 18 sampling steps\n",
" (768 x 768) image\n",
" Using a generic negative prompt\n",
"\n",
" Schedules:\n",
" Static guidance with scale of 9\n",
" Inverse kDecay (cosine variant) scheduled guidance\n",
" '''\n",
" # load the model\n",
" pipeline = load_model()\n",
"\n",
" # stores the output images\n",
" res = []\n",
"\n",
" # generate images with static and dynamic schedules\n",
" for (name,sched) in schedules.items():\n",
" # make the guidance norm\n",
" gtfm = cf_guidance.transforms.GuidanceTfm(sched)\n",
" # generate the image\n",
" with torch.autocast(device), torch.no_grad():\n",
" img = pipeline.generate(prompt, gtfm, **generation_kwargs)\n",
" # add the generated image\n",
" res.append(name)\n",
"\n",
" # return the generated images\n",
" return {\n",
" 'values': res,\n",
" 'label': 'Cosine vs. Static CFG'\n",
" }"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"\n",
"#| export\n",
"\n",
"iface = gr.Interface(\n",
" compare_dynamic_guidance,\n",
" inputs=\"text\",\n",
" outputs=gr.Gallery(),\n",
" title=\"Comparison with dynamic Classifier-free Guidance Comparison\",\n",
")\n",
"iface.launch()\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"import nbdev\n",
"nbdev.export.nb_export('app.ipynb', '')"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "sdiffkernel",
"language": "python",
"name": "sdiffkernel"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.8"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "7aa72ffd68a1153f913726b8656445c52d825f656451987cb25ebe84c64ea44d"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|