extern/easydiffusion
1
0
Fork 1
mirror of https://github.com/easydiffusion/easydiffusion.git synced 2025-04-14 14:38:26 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #357 from rbertus2000/beta

Browse Source 
fixed img_id for parallel renders
This commit is contained in:
cmdr2 2022-10-19 09:52:58 +05:30
parent 3de5f10d52
commit 44191cd908
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ui/sd_internal/runtime.py
View File

@ -206,6 +206,7 @@ def get_base_path(disk_path, session_id, prompt, img_id, ext, suffix=None):
os.makedirs(session_out_path, exist_ok=True) os.makedirs(session_out_path, exist_ok=True)
prompt_flattened = filename_regex.sub('_', prompt)[:50] prompt_flattened = filename_regex.sub('_', prompt)[:50]
if suffix is not None: if suffix is not None:
return os.path.join(session_out_path, f"{prompt_flattened}_{img_id}_{suffix}.{ext}") return os.path.join(session_out_path, f"{prompt_flattened}_{img_id}_{suffix}.{ext}")
@ -316,8 +317,7 @@ def do_mk_img(req: Request):
opt_f = 8 opt_f = 8
opt_ddim_eta = 0.0 opt_ddim_eta = 0.0
opt_init_img = req.init_image opt_init_img = req.init_image
img_id = base64.b64encode(int(time.time()).to_bytes(8, 'big')).decode() # Generate unique ID based on time.
img_id = img_id.translate({43:None, 47:None, 61:None})[-8:] # Remove + / = and keep last 8 chars.
print(req.to_string(), '\n device', device) print(req.to_string(), '\n device', device)
@ -462,6 +462,8 @@ def do_mk_img(req: Request):
print("saving images") print("saving images")
for i in range(batch_size): for i in range(batch_size):
img_id = base64.b64encode(int(time.time()+i).to_bytes(8, 'big')).decode() # Generate unique ID based on time.
img_id = img_id.translate({43:None, 47:None, 61:None})[-8:] # Remove + / = and keep last 8 chars.
x_samples_ddim = modelFS.decode_first_stage(x_samples[i].unsqueeze(0)) x_samples_ddim = modelFS.decode_first_stage(x_samples[i].unsqueeze(0))
x_sample = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0) x_sample = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)