Instructions to use kmpartner/xsds-fttest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use kmpartner/xsds-fttest with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("kmpartner/xsds-fttest", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Upload folder using huggingface_hub
Browse files- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scaler.pt +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2000/unet/config.json +69 -0
- checkpoint-2000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2000/unet_ema/config.json +76 -0
- checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- model_index.json +1 -1
- text_encoder/config.json +1 -1
- tokenizer/special_tokens_map.json +7 -1
- unet/config.json +1 -1
- unet/diffusion_pytorch_model.safetensors +1 -1
- vae/config.json +1 -1
checkpoint-2000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4f044a9ae8bcbc8b82b1e76ccb5556b3a2e8d34ca971251bd6ed8fe92fc2de9
|
| 3 |
+
size 2526204858
|
checkpoint-2000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea0f565f6312ec310f65f1b5934190efe8d1bf014dc307a989cf30f6cb1e463
|
| 3 |
+
size 14408
|
checkpoint-2000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c50a9cebe5d66d453d25b140738bff479749ac03e0a43597d8776bc22f6ed0c
|
| 3 |
+
size 988
|
checkpoint-2000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81a7fe0a2983de695c44ba167520d4ce1ca01157e36e90498bee8c9d8e4b61fc
|
| 3 |
+
size 1000
|
checkpoint-2000/unet/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "xsds-fttest/checkpoint-1000",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"attention_type": "default",
|
| 11 |
+
"block_out_channels": [
|
| 12 |
+
320,
|
| 13 |
+
640,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"center_input_sample": false,
|
| 17 |
+
"class_embed_type": null,
|
| 18 |
+
"class_embeddings_concat": false,
|
| 19 |
+
"conv_in_kernel": 3,
|
| 20 |
+
"conv_out_kernel": 3,
|
| 21 |
+
"cross_attention_dim": 768,
|
| 22 |
+
"cross_attention_norm": null,
|
| 23 |
+
"down_block_types": [
|
| 24 |
+
"DownBlock2D",
|
| 25 |
+
"CrossAttnDownBlock2D",
|
| 26 |
+
"CrossAttnDownBlock2D"
|
| 27 |
+
],
|
| 28 |
+
"downsample_padding": 1,
|
| 29 |
+
"dropout": 0.0,
|
| 30 |
+
"dual_cross_attention": false,
|
| 31 |
+
"encoder_hid_dim": null,
|
| 32 |
+
"encoder_hid_dim_type": null,
|
| 33 |
+
"flip_sin_to_cos": true,
|
| 34 |
+
"freq_shift": 0,
|
| 35 |
+
"in_channels": 4,
|
| 36 |
+
"layers_per_block": 1,
|
| 37 |
+
"mid_block_only_cross_attention": null,
|
| 38 |
+
"mid_block_scale_factor": 1,
|
| 39 |
+
"mid_block_type": null,
|
| 40 |
+
"norm_eps": 1e-05,
|
| 41 |
+
"norm_num_groups": 32,
|
| 42 |
+
"num_attention_heads": null,
|
| 43 |
+
"num_class_embeds": null,
|
| 44 |
+
"only_cross_attention": [
|
| 45 |
+
true,
|
| 46 |
+
false,
|
| 47 |
+
false
|
| 48 |
+
],
|
| 49 |
+
"out_channels": 4,
|
| 50 |
+
"projection_class_embeddings_input_dim": null,
|
| 51 |
+
"resnet_out_scale_factor": 1.0,
|
| 52 |
+
"resnet_skip_time_act": false,
|
| 53 |
+
"resnet_time_scale_shift": "default",
|
| 54 |
+
"reverse_transformer_layers_per_block": null,
|
| 55 |
+
"sample_size": 64,
|
| 56 |
+
"time_cond_proj_dim": null,
|
| 57 |
+
"time_embedding_act_fn": null,
|
| 58 |
+
"time_embedding_dim": null,
|
| 59 |
+
"time_embedding_type": "positional",
|
| 60 |
+
"timestep_post_act": null,
|
| 61 |
+
"transformer_layers_per_block": 1,
|
| 62 |
+
"up_block_types": [
|
| 63 |
+
"CrossAttnUpBlock2D",
|
| 64 |
+
"CrossAttnUpBlock2D",
|
| 65 |
+
"UpBlock2D"
|
| 66 |
+
],
|
| 67 |
+
"upcast_attention": false,
|
| 68 |
+
"use_linear_projection": false
|
| 69 |
+
}
|
checkpoint-2000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9d025f4b447b873801c0aa65c7ec69d6d051302cf0d39140939a90362ded2bd
|
| 3 |
+
size 1263018648
|
checkpoint-2000/unet_ema/config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "./xsds-fttest",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"attention_type": "default",
|
| 11 |
+
"block_out_channels": [
|
| 12 |
+
320,
|
| 13 |
+
640,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"center_input_sample": false,
|
| 17 |
+
"class_embed_type": null,
|
| 18 |
+
"class_embeddings_concat": false,
|
| 19 |
+
"conv_in_kernel": 3,
|
| 20 |
+
"conv_out_kernel": 3,
|
| 21 |
+
"cross_attention_dim": 768,
|
| 22 |
+
"cross_attention_norm": null,
|
| 23 |
+
"decay": 0.9999,
|
| 24 |
+
"down_block_types": [
|
| 25 |
+
"DownBlock2D",
|
| 26 |
+
"CrossAttnDownBlock2D",
|
| 27 |
+
"CrossAttnDownBlock2D"
|
| 28 |
+
],
|
| 29 |
+
"downsample_padding": 1,
|
| 30 |
+
"dropout": 0.0,
|
| 31 |
+
"dual_cross_attention": false,
|
| 32 |
+
"encoder_hid_dim": null,
|
| 33 |
+
"encoder_hid_dim_type": null,
|
| 34 |
+
"flip_sin_to_cos": true,
|
| 35 |
+
"freq_shift": 0,
|
| 36 |
+
"in_channels": 4,
|
| 37 |
+
"inv_gamma": 1.0,
|
| 38 |
+
"layers_per_block": 1,
|
| 39 |
+
"mid_block_only_cross_attention": null,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": null,
|
| 42 |
+
"min_decay": 0.0,
|
| 43 |
+
"norm_eps": 1e-05,
|
| 44 |
+
"norm_num_groups": 32,
|
| 45 |
+
"num_attention_heads": null,
|
| 46 |
+
"num_class_embeds": null,
|
| 47 |
+
"only_cross_attention": [
|
| 48 |
+
true,
|
| 49 |
+
false,
|
| 50 |
+
false
|
| 51 |
+
],
|
| 52 |
+
"optimization_step": 2000,
|
| 53 |
+
"out_channels": 4,
|
| 54 |
+
"power": 0.6666666666666666,
|
| 55 |
+
"projection_class_embeddings_input_dim": null,
|
| 56 |
+
"resnet_out_scale_factor": 1.0,
|
| 57 |
+
"resnet_skip_time_act": false,
|
| 58 |
+
"resnet_time_scale_shift": "default",
|
| 59 |
+
"reverse_transformer_layers_per_block": null,
|
| 60 |
+
"sample_size": 64,
|
| 61 |
+
"time_cond_proj_dim": null,
|
| 62 |
+
"time_embedding_act_fn": null,
|
| 63 |
+
"time_embedding_dim": null,
|
| 64 |
+
"time_embedding_type": "positional",
|
| 65 |
+
"timestep_post_act": null,
|
| 66 |
+
"transformer_layers_per_block": 1,
|
| 67 |
+
"up_block_types": [
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D",
|
| 70 |
+
"UpBlock2D"
|
| 71 |
+
],
|
| 72 |
+
"upcast_attention": false,
|
| 73 |
+
"update_after_step": 0,
|
| 74 |
+
"use_ema_warmup": false,
|
| 75 |
+
"use_linear_projection": false
|
| 76 |
+
}
|
checkpoint-2000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:468bd79810647c34c34eb74afd21bc4e11fcebc162ae8f5ad4aad05e4b38efb5
|
| 3 |
+
size 1263018648
|
model_index.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "StableDiffusionPipeline",
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
-
"_name_or_path": "
|
| 5 |
"feature_extractor": [
|
| 6 |
"transformers",
|
| 7 |
"CLIPFeatureExtractor"
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "StableDiffusionPipeline",
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "./xsds-fttest",
|
| 5 |
"feature_extractor": [
|
| 6 |
"transformers",
|
| 7 |
"CLIPFeatureExtractor"
|
text_encoder/config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"CLIPTextModel"
|
| 5 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "./xsds-fttest",
|
| 3 |
"architectures": [
|
| 4 |
"CLIPTextModel"
|
| 5 |
],
|
tokenizer/special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<|endoftext|>",
|
| 25 |
"lstrip": false,
|
unet/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DConditionModel",
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
-
"_name_or_path": "
|
| 5 |
"act_fn": "silu",
|
| 6 |
"addition_embed_type": null,
|
| 7 |
"addition_embed_type_num_heads": 64,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "UNet2DConditionModel",
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "xsds-fttest/checkpoint-1000",
|
| 5 |
"act_fn": "silu",
|
| 6 |
"addition_embed_type": null,
|
| 7 |
"addition_embed_type_num_heads": 64,
|
unet/diffusion_pytorch_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1263018648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:468bd79810647c34c34eb74afd21bc4e11fcebc162ae8f5ad4aad05e4b38efb5
|
| 3 |
size 1263018648
|
vae/config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKL",
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
-
"_name_or_path": "
|
| 5 |
"act_fn": "silu",
|
| 6 |
"block_out_channels": [
|
| 7 |
128,
|
|
|
|
| 1 |
{
|
| 2 |
"_class_name": "AutoencoderKL",
|
| 3 |
"_diffusers_version": "0.32.0.dev0",
|
| 4 |
+
"_name_or_path": "./xsds-fttest",
|
| 5 |
"act_fn": "silu",
|
| 6 |
"block_out_channels": [
|
| 7 |
128,
|