Commit
β’
453cb64
1
Parent(s):
3364451
End of training
Browse files- README.md +232 -10
- big-sdxl-lora.safetensors +1 -1
- big-sdxl-lora_emb.safetensors +2 -2
- image_0.png +2 -2
- image_1.png +2 -2
- image_2.png +2 -2
- image_3.png +2 -2
- pytorch_lora_weights.safetensors +1 -1
README.md
CHANGED
@@ -9,28 +9,28 @@ tags:
|
|
9 |
- template:sd-lora
|
10 |
widget:
|
11 |
|
12 |
-
- text: 'a photo of living room with
|
13 |
output:
|
14 |
url:
|
15 |
"image_0.png"
|
16 |
|
17 |
-
- text: 'a photo of living room with
|
18 |
output:
|
19 |
url:
|
20 |
"image_1.png"
|
21 |
|
22 |
-
- text: 'a photo of living room with
|
23 |
output:
|
24 |
url:
|
25 |
"image_2.png"
|
26 |
|
27 |
-
- text: 'a photo of living room with
|
28 |
output:
|
29 |
url:
|
30 |
"image_3.png"
|
31 |
|
32 |
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
33 |
-
instance_prompt: a photo of living room with
|
34 |
license: openrail++
|
35 |
---
|
36 |
|
@@ -51,7 +51,7 @@ license: openrail++
|
|
51 |
- On AUTOMATIC1111, load the LoRA by adding `<lora:big-sdxl-lora:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
|
52 |
- *Embeddings*: download **[`big-sdxl-lora_emb.safetensors` here πΎ](/prampampam/big-sdxl-lora/blob/main/big-sdxl-lora_emb.safetensors)**.
|
53 |
- Place it on it on your `embeddings` folder
|
54 |
-
- Use it by adding `big-sdxl-lora_emb` to your prompt. For example, `a photo of living room with
|
55 |
(you need both the LoRA and the embeddings as they were trained together for this LoRA)
|
56 |
|
57 |
|
@@ -67,10 +67,10 @@ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusi
|
|
67 |
pipeline.load_lora_weights('prampampam/big-sdxl-lora', weight_name='pytorch_lora_weights.safetensors')
|
68 |
embedding_path = hf_hub_download(repo_id='prampampam/big-sdxl-lora', filename='big-sdxl-lora_emb.safetensors', repo_type="model")
|
69 |
state_dict = load_file(embedding_path)
|
70 |
-
pipeline.load_textual_inversion(state_dict["clip_l"], token=[], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
|
71 |
-
pipeline.load_textual_inversion(state_dict["clip_g"], token=[], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
|
72 |
|
73 |
-
image = pipeline('a photo of living room with
|
74 |
```
|
75 |
|
76 |
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
@@ -79,7 +79,229 @@ For more details, including weighting, merging and fusing LoRAs, check the [docu
|
|
79 |
|
80 |
To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
|
81 |
|
82 |
-
to trigger concept `
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
83 |
|
84 |
|
85 |
|
|
|
9 |
- template:sd-lora
|
10 |
widget:
|
11 |
|
12 |
+
- text: 'a photo of living room with <s0><s1> and <s2><s3>'
|
13 |
output:
|
14 |
url:
|
15 |
"image_0.png"
|
16 |
|
17 |
+
- text: 'a photo of living room with <s0><s1> and <s2><s3>'
|
18 |
output:
|
19 |
url:
|
20 |
"image_1.png"
|
21 |
|
22 |
+
- text: 'a photo of living room with <s0><s1> and <s2><s3>'
|
23 |
output:
|
24 |
url:
|
25 |
"image_2.png"
|
26 |
|
27 |
+
- text: 'a photo of living room with <s0><s1> and <s2><s3>'
|
28 |
output:
|
29 |
url:
|
30 |
"image_3.png"
|
31 |
|
32 |
base_model: stabilityai/stable-diffusion-xl-base-1.0
|
33 |
+
instance_prompt: a photo of living room with <s0><s1> and <s2><s3> in scandinavic style
|
34 |
license: openrail++
|
35 |
---
|
36 |
|
|
|
51 |
- On AUTOMATIC1111, load the LoRA by adding `<lora:big-sdxl-lora:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
|
52 |
- *Embeddings*: download **[`big-sdxl-lora_emb.safetensors` here πΎ](/prampampam/big-sdxl-lora/blob/main/big-sdxl-lora_emb.safetensors)**.
|
53 |
- Place it on it on your `embeddings` folder
|
54 |
+
- Use it by adding `big-sdxl-lora_emb` to your prompt. For example, `a photo of living room with big-sdxl-lora_emb and in scandinavic style`
|
55 |
(you need both the LoRA and the embeddings as they were trained together for this LoRA)
|
56 |
|
57 |
|
|
|
67 |
pipeline.load_lora_weights('prampampam/big-sdxl-lora', weight_name='pytorch_lora_weights.safetensors')
|
68 |
embedding_path = hf_hub_download(repo_id='prampampam/big-sdxl-lora', filename='big-sdxl-lora_emb.safetensors', repo_type="model")
|
69 |
state_dict = load_file(embedding_path)
|
70 |
+
pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>", "<s2>", "<s3>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
|
71 |
+
pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>", "<s2>", "<s3>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
|
72 |
|
73 |
+
image = pipeline('a photo of living room with <s0><s1> and <s2><s3>').images[0]
|
74 |
```
|
75 |
|
76 |
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
|
|
79 |
|
80 |
To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
|
81 |
|
82 |
+
to trigger concept `TOK49986` β use `<s0><s1>` in your prompt
|
83 |
+
|
84 |
+
|
85 |
+
to trigger concept `TOK52817` β use `<s2><s3>` in your prompt
|
86 |
+
|
87 |
+
|
88 |
+
to trigger concept `TOK98678` β use `<s4><s5>` in your prompt
|
89 |
+
|
90 |
+
|
91 |
+
to trigger concept `TOK113071` β use `<s6><s7>` in your prompt
|
92 |
+
|
93 |
+
|
94 |
+
to trigger concept `TOK120149` β use `<s8><s9>` in your prompt
|
95 |
+
|
96 |
+
|
97 |
+
to trigger concept `TOK123556` β use `<s10><s11>` in your prompt
|
98 |
+
|
99 |
+
|
100 |
+
to trigger concept `TOK135534` β use `<s12><s13>` in your prompt
|
101 |
+
|
102 |
+
|
103 |
+
to trigger concept `TOK189670` β use `<s14><s15>` in your prompt
|
104 |
+
|
105 |
+
|
106 |
+
to trigger concept `TOK190562` β use `<s16><s17>` in your prompt
|
107 |
+
|
108 |
+
|
109 |
+
to trigger concept `TOK193714` β use `<s18><s19>` in your prompt
|
110 |
+
|
111 |
+
|
112 |
+
to trigger concept `TOK241048` β use `<s20><s21>` in your prompt
|
113 |
+
|
114 |
+
|
115 |
+
to trigger concept `TOK250041` β use `<s22><s23>` in your prompt
|
116 |
+
|
117 |
+
|
118 |
+
to trigger concept `TOK268959` β use `<s24><s25>` in your prompt
|
119 |
+
|
120 |
+
|
121 |
+
to trigger concept `TOK273000` β use `<s26><s27>` in your prompt
|
122 |
+
|
123 |
+
|
124 |
+
to trigger concept `TOK277813` β use `<s28><s29>` in your prompt
|
125 |
+
|
126 |
+
|
127 |
+
to trigger concept `TOK279746` β use `<s30><s31>` in your prompt
|
128 |
+
|
129 |
+
|
130 |
+
to trigger concept `TOK295935` β use `<s32><s33>` in your prompt
|
131 |
+
|
132 |
+
|
133 |
+
to trigger concept `TOK305227` β use `<s34><s35>` in your prompt
|
134 |
+
|
135 |
+
|
136 |
+
to trigger concept `TOK309606` β use `<s36><s37>` in your prompt
|
137 |
+
|
138 |
+
|
139 |
+
to trigger concept `TOK321136` β use `<s38><s39>` in your prompt
|
140 |
+
|
141 |
+
|
142 |
+
to trigger concept `TOK329781` β use `<s40><s41>` in your prompt
|
143 |
+
|
144 |
+
|
145 |
+
to trigger concept `TOK329782` β use `<s42><s43>` in your prompt
|
146 |
+
|
147 |
+
|
148 |
+
to trigger concept `TOK352259` β use `<s44><s45>` in your prompt
|
149 |
+
|
150 |
+
|
151 |
+
to trigger concept `TOK355638` β use `<s46><s47>` in your prompt
|
152 |
+
|
153 |
+
|
154 |
+
to trigger concept `TOK357399` β use `<s48><s49>` in your prompt
|
155 |
+
|
156 |
+
|
157 |
+
to trigger concept `TOK368921` β use `<s50><s51>` in your prompt
|
158 |
+
|
159 |
+
|
160 |
+
to trigger concept `TOK377236` β use `<s52><s53>` in your prompt
|
161 |
+
|
162 |
+
|
163 |
+
to trigger concept `TOK382924` β use `<s54><s55>` in your prompt
|
164 |
+
|
165 |
+
|
166 |
+
to trigger concept `TOK405550` β use `<s56><s57>` in your prompt
|
167 |
+
|
168 |
+
|
169 |
+
to trigger concept `TOK429026` β use `<s58><s59>` in your prompt
|
170 |
+
|
171 |
+
|
172 |
+
to trigger concept `TOK434773` β use `<s60><s61>` in your prompt
|
173 |
+
|
174 |
+
|
175 |
+
to trigger concept `TOK435237` β use `<s62><s63>` in your prompt
|
176 |
+
|
177 |
+
|
178 |
+
to trigger concept `TOK437871` β use `<s64><s65>` in your prompt
|
179 |
+
|
180 |
+
|
181 |
+
to trigger concept `TOK439185` β use `<s66><s67>` in your prompt
|
182 |
+
|
183 |
+
|
184 |
+
to trigger concept `TOK439384` β use `<s68><s69>` in your prompt
|
185 |
+
|
186 |
+
|
187 |
+
to trigger concept `TOK443869` β use `<s70><s71>` in your prompt
|
188 |
+
|
189 |
+
|
190 |
+
to trigger concept `TOK444874` β use `<s72><s73>` in your prompt
|
191 |
+
|
192 |
+
|
193 |
+
to trigger concept `TOK453903` β use `<s74><s75>` in your prompt
|
194 |
+
|
195 |
+
|
196 |
+
to trigger concept `TOK465250` β use `<s76><s77>` in your prompt
|
197 |
+
|
198 |
+
|
199 |
+
to trigger concept `TOK482466` β use `<s78><s79>` in your prompt
|
200 |
+
|
201 |
+
|
202 |
+
to trigger concept `TOK503940` β use `<s80><s81>` in your prompt
|
203 |
+
|
204 |
+
|
205 |
+
to trigger concept `TOK524768` β use `<s82><s83>` in your prompt
|
206 |
+
|
207 |
+
|
208 |
+
to trigger concept `TOK536204` β use `<s84><s85>` in your prompt
|
209 |
+
|
210 |
+
|
211 |
+
to trigger concept `TOK537466` β use `<s86><s87>` in your prompt
|
212 |
+
|
213 |
+
|
214 |
+
to trigger concept `TOK547839` β use `<s88><s89>` in your prompt
|
215 |
+
|
216 |
+
|
217 |
+
to trigger concept `TOK548004` β use `<s90><s91>` in your prompt
|
218 |
+
|
219 |
+
|
220 |
+
to trigger concept `TOK549578` β use `<s92><s93>` in your prompt
|
221 |
+
|
222 |
+
|
223 |
+
to trigger concept `TOK557244` β use `<s94><s95>` in your prompt
|
224 |
+
|
225 |
+
|
226 |
+
to trigger concept `TOK561859` β use `<s96><s97>` in your prompt
|
227 |
+
|
228 |
+
|
229 |
+
to trigger concept `TOK569103` β use `<s98><s99>` in your prompt
|
230 |
+
|
231 |
+
|
232 |
+
to trigger concept `TOK569104` β use `<s100><s101>` in your prompt
|
233 |
+
|
234 |
+
|
235 |
+
to trigger concept `TOK570087` β use `<s102><s103>` in your prompt
|
236 |
+
|
237 |
+
|
238 |
+
to trigger concept `TOK577885` β use `<s104><s105>` in your prompt
|
239 |
+
|
240 |
+
|
241 |
+
to trigger concept `TOK578163` β use `<s106><s107>` in your prompt
|
242 |
+
|
243 |
+
|
244 |
+
to trigger concept `TOK586036` β use `<s108><s109>` in your prompt
|
245 |
+
|
246 |
+
|
247 |
+
to trigger concept `TOK590747` β use `<s110><s111>` in your prompt
|
248 |
+
|
249 |
+
|
250 |
+
to trigger concept `TOK592708` β use `<s112><s113>` in your prompt
|
251 |
+
|
252 |
+
|
253 |
+
to trigger concept `TOK597750` β use `<s114><s115>` in your prompt
|
254 |
+
|
255 |
+
|
256 |
+
to trigger concept `TOK603453` β use `<s116><s117>` in your prompt
|
257 |
+
|
258 |
+
|
259 |
+
to trigger concept `TOK618877` β use `<s118><s119>` in your prompt
|
260 |
+
|
261 |
+
|
262 |
+
to trigger concept `TOK619268` β use `<s120><s121>` in your prompt
|
263 |
+
|
264 |
+
|
265 |
+
to trigger concept `TOK629015` β use `<s122><s123>` in your prompt
|
266 |
+
|
267 |
+
|
268 |
+
to trigger concept `TOK631826` β use `<s124><s125>` in your prompt
|
269 |
+
|
270 |
+
|
271 |
+
to trigger concept `TOK639063` β use `<s126><s127>` in your prompt
|
272 |
+
|
273 |
+
|
274 |
+
to trigger concept `TOK639380` β use `<s128><s129>` in your prompt
|
275 |
+
|
276 |
+
|
277 |
+
to trigger concept `TOK648242` β use `<s130><s131>` in your prompt
|
278 |
+
|
279 |
+
|
280 |
+
to trigger concept `TOK651623` β use `<s132><s133>` in your prompt
|
281 |
+
|
282 |
+
|
283 |
+
to trigger concept `TOK653420` β use `<s134><s135>` in your prompt
|
284 |
+
|
285 |
+
|
286 |
+
to trigger concept `TOK654567` β use `<s136><s137>` in your prompt
|
287 |
+
|
288 |
+
|
289 |
+
to trigger concept `TOK657274` β use `<s138><s139>` in your prompt
|
290 |
+
|
291 |
+
|
292 |
+
to trigger concept `TOK658513` β use `<s140><s141>` in your prompt
|
293 |
+
|
294 |
+
|
295 |
+
to trigger concept `TOK662375` β use `<s142><s143>` in your prompt
|
296 |
+
|
297 |
+
|
298 |
+
to trigger concept `TOK664555` β use `<s144><s145>` in your prompt
|
299 |
+
|
300 |
+
|
301 |
+
to trigger concept `TOK674941` β use `<s146><s147>` in your prompt
|
302 |
+
|
303 |
+
|
304 |
+
to trigger concept `TOK679104` β use `<s148><s149>` in your prompt
|
305 |
|
306 |
|
307 |
|
big-sdxl-lora.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46698072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a0e942a15c09fcf431dc70f00ffd78a8832240fe2523c1d46f22109b6fc4071
|
3 |
size 46698072
|
big-sdxl-lora_emb.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b71ad85418914e5a7e11cc501c1c22c2f2c4eaa3b775f3d024795be18a61cc
|
3 |
+
size 1228960
|
image_0.png
CHANGED
![]() |
Git LFS Details
|
![]() |
Git LFS Details
|
image_1.png
CHANGED
![]() |
Git LFS Details
|
![]() |
Git LFS Details
|
image_2.png
CHANGED
![]() |
Git LFS Details
|
![]() |
Git LFS Details
|
image_3.png
CHANGED
![]() |
Git LFS Details
|
![]() |
Git LFS Details
|
pytorch_lora_weights.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46615272
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96153332f8e07c99304dd804d47849d25f4abce1078f518ff4b9c98647f0dcbd
|
3 |
size 46615272
|